© 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. 80957
    Prev
    Next
    INDEX
    Explanations

    pro- or pre- prefixes

    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
     suspension
    -0.79
     constantly
    -0.74
    简历
    -0.73
     manuelle
    -0.72
    ^{*}
    -0.71
    mặt
    -0.69
     Biochemical
    -0.68
     can
    -0.67
    OrEqualTo
    -0.67
     specialty
    -0.66
    POSITIVE LOGITS
    buenos
    0.84
    México
    0.79
     voorwaarden
    0.78
    gebob
    0.77
    Auszeichnungen
    0.73
    BH
    0.72
    export
    0.71
     massac
    0.71
    ursor
    0.70
     troppo
    0.69
    Activations Density 0.071%

    No Known Activations