© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39042
    Prev
    Next
    INDEX
    Explanations

    ii ProQuest document

    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
     nekaj
    -0.94
     большое
    -0.86
    riak
    -0.86
    ↵↵↵↵↵↵↵↵↵↵↵
    -0.86
     ailleurs
    -0.85
    kan
    -0.84
    ↵↵↵↵↵
    -0.82
     xxiii
    -0.82
     Delhi
    -0.82
     Weihnachten
    -0.81
    POSITIVE LOGITS
     Igual
    0.93
    maten
    0.90
     pimenta
    0.90
     piment
    0.86
    ongono
    0.84
    파일
    0.84
    囧
    0.84
    вес
    0.82
     Só
    0.82
    pruch
    0.82
    Activations Density 0.009%

    No Known Activations