© 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. 138483
    Prev
    Next
    INDEX
    Explanations

    graphics card

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

    early cases linked to market

    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
    御
    0.48
    茎
    0.46
    ผสม
    0.45
    八
    0.45
    Growing
    0.44
     細
    0.43
    ខ
    0.43
    ົາ
    0.43
    Cuenta
    0.43
    ５
    0.43
    POSITIVE LOGITS
     games
    0.44
     Cou
    0.44
     candidatura
    0.43
     debacle
    0.43
     resc
    0.43
    atorul
    0.42
     N
    0.42
     Nar
    0.42
     dormir
    0.42
     complicate
    0.42
    Activations Density 0.001%

    No Known Activations