© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99202
    Prev
    Next
    INDEX
    Explanations

    fixed-width integer types

    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
    ьте
    -0.84
     although
    -0.82
     arbeitet
    -0.81
    牟
    -0.73
    ʋ
    -0.72
    чний
    -0.70
     Asso
    -0.69
    っかり
    -0.69
    locality
    -0.69
    ラー
    -0.69
    POSITIVE LOGITS
    ایز
    0.80
    Observation
    0.79
    studie
    0.78
    bitset
    0.77
    ཥ
    0.77
    Mab
    0.76
     temporaire
    0.75
    grazie
    0.75
     Италии
    0.75
    truk
    0.75
    Activations Density 0.025%

    No Known Activations