© 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. 10-GEMMASCOPE-RES-131K
    7. 101772
    Prev
    Next
    INDEX
    Explanations

    Bolsheviks and failover

    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_10/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
    ՙ
    -1.85
     Their
    -1.81
    </h5>
    -1.80
     lances
    -1.79
    翾
    -1.74
    ídas
    -1.73
    酲
    -1.73
    鱘
    -1.71
    viembre
    -1.69
    阇
    -1.69
    POSITIVE LOGITS
     but
    1.95
    悄悄
    1.68
    —
    1.63
     to
    1.60
     программ
    1.57
     такое
    1.55
    )
    1.53
    なの
    1.53
    4
    1.51
     et
    1.50
    Activations Density 0.043%

    No Known Activations