© 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. 183638
    Prev
    Next
    INDEX
    Explanations

    He could, he learned

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

    evolving landscape

    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
     સરળ
    0.60
     आयुष्य
    0.55
    彠
    0.54
     घेण्यासाठी
    0.54
     снова
    0.53
     Wszyst
    0.53
    無需
    0.53
     zdoby
    0.53
     Alltag
    0.53
     Ogni
    0.53
    POSITIVE LOGITS
    पूर्ति
    0.48
    t
    0.47
     phosphoric
    0.44
     as
    0.44
     liquidity
    0.44
     bazaar
    0.43
     lay
    0.43
     vali
    0.43
     gin
    0.42
     portfolios
    0.42
    Activations Density 0.000%

    No Known Activations