© 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. 93418
    Prev
    Next
    INDEX
    Explanations

    code syntax elements

    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
    gura
    -0.89
     heat
    -0.83
     רק
    -0.83
    bsd
    -0.82
     garota
    -0.81
     head
    -0.80
    ℚ
    -0.80
    ye
    -0.79
    ーフ
    -0.78
     progressive
    -0.77
    POSITIVE LOGITS
     as
    1.70
    oprecip
    0.85
     than
    0.83
    ┃
    0.82
    あれば
    0.80
    weiten
    0.80
     llamado
    0.77
    called
    0.77
    .*;
    0.76
    Acest
    0.76
    Activations Density 0.036%

    No Known Activations