© 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. 34-GEMMASCOPE-RES-131K
    7. 62834
    Prev
    Next
    INDEX
    Explanations

    Swamy names and Skanda

    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
     CDs
    -0.71
    tığı
    -0.70
    tte
    -0.69
    才能
    -0.69
    md
    -0.69
     dedic
    -0.68
     ^{-
    -0.67
    细
    -0.66
    SOL
    -0.66
     सम
    -0.66
    POSITIVE LOGITS
     સ્
    1.07
     സ്
    0.89
    explosion
    0.84
    lenül
    0.84
     스
    0.83
    cknowled
    0.83
     what
    0.82
     esclavos
    0.82
    IDL
    0.82
    ástico
    0.81
    Activations Density 0.008%

    No Known Activations