© 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. 62097
    Prev
    Next
    INDEX
    Explanations

    dates and months

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

    conditions, assignments, or restrictions

    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
    িয়া
    0.47
    ু
    0.46
    是用
    0.46
    গা
    0.45
    精致
    0.44
    гер
    0.43
    Wedding
    0.43
    colorPrimary
    0.42
    狎
    0.42
    awar
    0.42
    POSITIVE LOGITS
     أص
    0.46
     október
    0.44
     released
    0.43
     december
    0.43
     Released
    0.43
    鋐
    0.42
    ٣
    0.41
     ജ
    0.41
    Released
    0.41
     november
    0.41
    Activations Density 0.000%

    No Known Activations