© 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. 22-GEMMASCOPE-RES-131K
    7. 70654
    Prev
    Next
    INDEX
    Explanations

    Hebrew, Arabic, English words

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    There
    -2.58
    It
    -2.56
    Just
    -2.22
    While
    -2.22
    At
    -2.20
    Even
    -2.13
    When
    -2.11
    Only
    -2.08
    Some
    -2.08
     and
    -2.08
    POSITIVE LOGITS
    ఽ
    2.14
    镲
    2.11
    ᕮ
    2.09
    籥
    1.97
    Hmmm
    1.97
    蓠
    1.92
    commonly
    1.92
    idk
    1.91
    秾
    1.90
     amd
    1.88
    Activations Density 0.001%

    No Known Activations