© 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. 79694
    Prev
    Next
    INDEX
    Explanations

    macro names

    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
     it
    -1.18
    armani
    -0.93
     then
    -0.93
     dont
    -0.91
     only
    -0.89
     къде
    -0.86
     poziomie
    -0.85
     not
    -0.85
    ≧
    -0.84
     dann
    -0.84
    POSITIVE LOGITS
     crescita
    0.96
     スタン
    0.91
    fficient
    0.91
    balleur
    0.90
     Lmao
    0.90
     aprire
    0.90
    ’;
    0.90
    lysm
    0.89
    Jap
    0.88
     Impressive
    0.87
    Activations Density 0.019%

    No Known Activations