© 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. 244617
    Prev
    Next
    INDEX
    Explanations

    wants to switch to community

    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
    clientX
    0.46
    fund
    0.45
    ffect
    0.45
    time
    0.44
    effect
    0.44
    ų
    0.44
    oe
    0.43
    response
    0.43
    ERROR
    0.43
     kijken
    0.43
    POSITIVE LOGITS
     Amat
    0.47
     غیر
    0.47
     bày
    0.45
     tolls
    0.44
    ⓑ
    0.44
    城県
    0.44
     arqu
    0.44
     criação
    0.43
     Masa
    0.43
     afar
    0.43
    Activations Density 0.000%

    No Known Activations