© 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. 22-GEMMASCOPE-RES-131K
    7. 72661
    Prev
    Next
    INDEX
    Explanations

    introducing key 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_22/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
     Când
    -0.88
    Gf
    -0.86
    :{
    -0.85
    ({
    -0.85
    FFE
    -0.84
     guantes
    -0.82
    apatan
    -0.79
     otoño
    -0.79
     resté
    -0.78
    龈
    -0.78
    POSITIVE LOGITS
    Descriere
    1.15
     but
    1.13
    нология
    1.01
    حيات
    1.00
     کیلومتر
    0.96
     resili
    0.93
     ocasion
    0.93
    خخ
    0.93
    Katso
    0.92
    Turbul
    0.92
    Activations Density 0.000%

    No Known Activations