© 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. 62134
    Prev
    Next
    INDEX
    Explanations

    settlement, limit, reporting, demands, other, co-executive, nearby, building, for

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

    context window

    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
     mw
    0.51
     primeiros
    0.47
    };
    0.46
     tia
    0.45
     cutter
    0.44
     contamos
    0.44
     collectively
    0.43
     market
    0.43
     privacy
    0.42
     كرد
    0.42
    POSITIVE LOGITS
    s
    0.56
    ında
    0.54
    də
    0.53
    hib
    0.52
    rame
    0.52
    raj
    0.52
    kör
    0.52
    テク
    0.50
    etään
    0.50
    alary
    0.50
    Activations Density 0.000%

    No Known Activations