© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 67279
    Prev
    Next
    INDEX
    Explanations

    longtime descriptor

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

    the occurrence of the phrase “long time” (including its hyphenated or concatenated forms).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     last
    -1.38
     último
    -1.31
     afgelopen
    -1.21
    ázaro
    -1.20
    に関しては
    -1.18
    が少ない
    -1.16
     publicó
    -1.16
     belangrijk
    -1.11
     času
    -1.11
    ToLoad
    -1.09
    POSITIVE LOGITS
     ancak
    1.37
     and
    1.37
    '
    1.36
    ’
    1.34
     ollut
    1.34
    .”
    1.31
     —
    1.25
     –
    1.18
     (>
    1.18
     ιστο
    1.15
    Activations Density 0.029%

    No Known Activations