© 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. 194276
    Prev
    Next
    INDEX
    Explanations

    loan access, race engineering, character, subcontract

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

    flamingo lawn

    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
     Hành
    0.52
     Outreach
    0.50
    ាស់
    0.47
     Karaoke
    0.46
     Oh
    0.45
     Ornamental
    0.45
     Would
    0.45
    塢
    0.45
     Audible
    0.44
     Organis
    0.44
    POSITIVE LOGITS
     descom
    0.51
    rees
    0.46
    R
    0.46
    opy
    0.45
     accumulating
    0.45
    8
    0.45
    óz
    0.45
    6
    0.45
     суб
    0.45
    ノル
    0.44
    Activations Density 0.000%

    No Known Activations