© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 69577
    Prev
    Next
    INDEX
    Explanations

    academic programs, thousands of, receive user, uneven tread, Trialogue, more skills

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

    else

    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
     sociis
    0.49
    ख्य
    0.47
    ষেধ
    0.46
     upto
    0.46
     findPlayer
    0.45
    лимп
    0.44
     elytra
    0.44
    }$;
    0.43
    вете
    0.43
    лля
    0.43
    POSITIVE LOGITS
    second
    0.49
    decision
    0.46
    investissement
    0.46
    Brit
    0.45
    A
    0.44
    ident
    0.43
    iter
    0.43
    icing
    0.43
    computing
    0.43
     شکست
    0.42
    Activations Density 0.000%

    No Known Activations