© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13871
    Prev
    Next
    INDEX
    Explanations

    absence of things

    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_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
    휀
    -1.97
    趼
    -1.91
    퐼
    -1.88
    垟
    -1.84
    搋
    -1.76
    櫺
    -1.75
    ㍑
    -1.73
    豋
    -1.72
    烀
    -1.70
     applau
    -1.67
    POSITIVE LOGITS
     only
    2.13
     from
    1.87
     After
    1.86
     after
    1.84
     for
    1.80
     >
    1.75
     Only
    1.70
    :
    1.70
     that
    1.66
     For
    1.63
    Activations Density 0.044%

    No Known Activations