© 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. 168988
    Prev
    Next
    INDEX
    Explanations

    saving money on

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

    Void retrieval feeding holds following knowledge

    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
     giúp
    0.53
    幸
    0.48
     hilft
    0.47
    ੁ
    0.47
    養
    0.47
     организаций
    0.47
    質問
    0.47
    醫師
    0.47
    物品
    0.47
    員
    0.46
    POSITIVE LOGITS
     ,
    0.61
     foresee
    0.49
     Chow
    0.49
    toon
    0.49
    monospace
    0.48
     Minsk
    0.46
    millimeters
    0.46
    piej
    0.46
    defined
    0.45
    Overflow
    0.45
    Activations Density 0.000%

    No Known Activations