© 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. 49900
    Prev
    Next
    INDEX
    Explanations

    following equation

    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
     tekst
    -0.96
    踵
    -0.92
     preciosa
    -0.90
     filme
    -0.88
     zv
    -0.88
    çe
    -0.87
     بای
    -0.82
    cero
    -0.82
    የ
    -0.82
     italiano
    -0.81
    POSITIVE LOGITS
    INSEE
    0.91
     giudizio
    0.91
     profonda
    0.90
    Acceptable
    0.88
     чаще
    0.88
     deeper
    0.88
     produrre
    0.87
     入り口
    0.86
    TECN
    0.86
    cách
    0.85
    Activations Density 0.000%

    No Known Activations