© 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. 209063
    Prev
    Next
    INDEX
    Explanations

    `to` followed by specific tokens

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

    describing items, specifications, or conditions

    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
    ריק
    0.48
    nullable
    0.45
    クリスマス
    0.45
    gesteld
    0.45
    जाने
    0.44
     기준으로
    0.43
    ﺽ
    0.43
    정도
    0.43
    தே
    0.43
     amplit
    0.43
    POSITIVE LOGITS
    Techn
    0.53
    Undo
    0.48
    ateur
    0.48
     осве
    0.47
     साधन
    0.45
     Lulu
    0.44
     داع
    0.44
     техники
    0.44
     Techno
    0.44
     ويكي
    0.43
    Activations Density 0.000%

    No Known Activations