© 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. 34-GEMMASCOPE-RES-131K
    7. 23679
    Prev
    Next
    INDEX
    Explanations

    numbers including 89

    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_34/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
     strane
    -0.89
    ֛
    -0.89
     Senhora
    -0.87
     you
    -0.83
    vignon
    -0.81
     Esses
    -0.81
    弱点
    -0.81
     vesel
    -0.80
     vitre
    -0.80
     montón
    -0.79
    POSITIVE LOGITS
     intensively
    0.88
     aceptas
    0.88
     concluding
    0.85
     DAMN
    0.85
     there
    0.84
    zcze
    0.81
    只好
    0.81
     gebra
    0.79
    лі
    0.78
    iore
    0.78
    Activations Density 0.018%

    No Known Activations