© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 26690
    Prev
    Next
    INDEX
    Explanations

    categories and specifics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    🍄
    0.42
    Strategic
    0.40
    蘑
    0.38
     Desmond
    0.37
    landmark
    0.36
    ær
    0.36
    庄
    0.36
    曠
    0.36
    мпания
    0.36
     કરવી
    0.35
    POSITIVE LOGITS
     adat
    0.44
     Inet
    0.39
     Solver
    0.39
     레
    0.38
     iron
    0.38
     alphabetical
    0.38
    હાર
    0.37
     narrow
    0.36
     experiments
    0.36
     Sindh
    0.36
    Activations Density 0.001%

    No Known Activations