© 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. 96775
    Prev
    Next
    INDEX
    Explanations

    supermarkets European, international family, fighter F

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

    monitoring and follow-up

    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
    浿
    0.47
    ಣ
    0.45
     kostenlos
    0.43
     daytime
    0.43
     günd
    0.43
    .#
    0.42
    午後
    0.42
     developing
    0.42
     baya
    0.42
    逻
    0.42
    POSITIVE LOGITS
    oh
    0.52
    ons
    0.52
    that
    0.50
    acier
    0.50
    agno
    0.48
    niches
    0.48
    ajos
    0.46
    losses
    0.45
    agod
    0.44
    hém
    0.44
    Activations Density 0.001%

    No Known Activations