© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 60339
    Prev
    Next
    INDEX
    Explanations

    license files and terms

    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
     delivers
    -0.73
    三日
    -0.73
    ůž
    -0.72
    НОЙ
    -0.72
    コーナー
    -0.71
     dispersion
    -0.71
     papá
    -0.71
     quema
    -0.68
     sok
    -0.68
     produces
    -0.68
    POSITIVE LOGITS
     Ctr
    0.82
    HIN
    0.82
     integ
    0.80
    フレ
    0.79
     nugget
    0.76
     Parole
    0.76
     harde
    0.76
     السيا
    0.75
    ൗ
    0.75
     âges
    0.74
    Activations Density 0.004%

    No Known Activations