© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 25345
    Prev
    Next
    INDEX
    Explanations

    names and dates

    np_acts-logits-general · gemini-2.5-flash-lite

    scheduling and optimizing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Detect
    0.45
    中止
    0.45
     الخارجية
    0.44
    ಹಾರ
    0.43
     seizures
    0.43
    衄
    0.40
     जब्त
    0.40
     quantità
    0.40
     منح
    0.40
     उचित
    0.39
    POSITIVE LOGITS
     London
    0.44
     ओर
    0.41
    andinavian
    0.41
     replaces
    0.41
     REVIEW
    0.41
    돌
    0.40
     address
    0.40
     addresses
    0.40
     Doll
    0.40
     adres
    0.40
    Activations Density 0.000%

    No Known Activations