© 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. 131249
    Prev
    Next
    INDEX
    Explanations

    efficient abandon

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

    industry wide activities

    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
    子は
    0.49
     DataFrame
    0.47
    Default
    0.45
     بیم
    0.45
     軍
    0.45
    ponse
    0.44
     배열
    0.44
     Pope
    0.44
     Coco
    0.44
    ләре
    0.44
    POSITIVE LOGITS
    h
    0.48
    INN
    0.46
    सव
    0.45
    LOAD
    0.45
    nú
    0.45
    grabbing
    0.45
    WOOD
    0.45
    electro
    0.45
    hala
    0.44
    rational
    0.43
    Activations Density 0.000%

    No Known Activations