© 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. 51619
    Prev
    Next
    INDEX
    Explanations

    these countries

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

    AI, Mac, Pro models

    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
     cuchar
    0.47
     gafas
    0.46
     culto
    0.46
     gratuito
    0.46
     educativas
    0.44
     синте
    0.43
     flavoured
    0.43
     剤
    0.43
     लड़की
    0.43
     علاج
    0.42
    POSITIVE LOGITS
     along
    0.46
    岭
    0.44
    south
    0.44
     southernmost
    0.43
    Configurations
    0.43
     gardens
    0.42
     whence
    0.42
    ⛰
    0.42
    compose
    0.42
    oreau
    0.42
    Activations Density 0.000%

    No Known Activations