© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 42764
    Prev
    Next
    INDEX
    Explanations

    abbreviation or initialism prefix

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is highly sensitive to the exact token "cf" (e.g. in variable names or reference labels).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    the occurrence of the "cf" token or prefix, especially within code identifiers, tags, or hexadecimal/hash strings.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    the token "cf" (often as part of variable names, file paths, or technical abbreviations in code).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tetapi
    -2.94
    悒
    -2.58
    鼙
    -2.53
    唞
    -2.47
    。】
    -2.47
    ם
    -2.45
    獃
    -2.45
    ;
    -2.44
    檠
    -2.42
    )
    -2.41
    POSITIVE LOGITS
    '
    3.09
    にします
    2.58
    y
    2.52
    cf
    2.48
    少ない
    2.47
    のだが
    2.45
    遢
    2.41
    荩
    2.41
     увидел
    2.39
    งิน
    2.38
    Activations Density 0.001%

    No Known Activations