© 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. 69287
    Prev
    Next
    INDEX
    Explanations

    personal experiences

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

    county records

    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
    a
    0.51
    ه
    0.48
     машине
    0.47
     électriques
    0.46
     केलेली
    0.46
     SR
    0.45
    न
    0.44
     इलाके
    0.43
     trại
    0.43
    一年
    0.42
    POSITIVE LOGITS
     Provides
    0.52
    StrTo
    0.52
     發
    0.51
     Objetivo
    0.48
     取り
    0.48
     nimmt
    0.48
     Tvam
    0.48
     Allows
    0.47
     Пользова
    0.47
    ⏺
    0.47
    Activations Density 0.000%

    No Known Activations