© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112619
    Prev
    Next
    INDEX
    Explanations

    Karyometry, enough about, Line’s

    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
    栳
    -2.06
     sebel
    -1.77
    )"
    -1.75
     '-
    -1.73
     Selama
    -1.71
    鷓
    -1.71
     Sebab
    -1.68
     Tetapi
    -1.67
    ."
    -1.66
     "-
    -1.66
    POSITIVE LOGITS
     There
    2.20
     Максима
    1.99
     Some
    1.98
    衚
    1.98
    余談
    1.96
     eliminates
    1.95
     邊
    1.93
    sika
    1.86
     prevents
    1.85
     壓
    1.83
    Activations Density 0.000%

    No Known Activations