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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100990
    Prev
    Next
    INDEX
    Explanations

    anti-Xa

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

    hexadecimal notation indicators, particularly "0xA" and related hex prefixes.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron activates on hexadecimal numeric literals—particularly sequences like “\x..” or “xa..” where “x” is followed by hex digits.

    oai_token-act-pair · o4-miniTriggered 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
    瑧
    -3.06
    鸰
    -2.95
    With
    -2.73
     möjlighet
    -2.66
     behövs
    -2.55
     händer
    -2.55
    which
    -2.55
     htons
    -2.53
    メリカ
    -2.47
     mulia
    -2.47
    POSITIVE LOGITS
    ౭
    2.92
     einzigen
    2.91
    謦
    2.83
    薆
    2.70
    "
    2.70
     haupts
    2.47
    缯
    2.44
    觏
    2.38
     he
    2.34
     ."
    2.34
    Activations Density 0.004%

    No Known Activations