© 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. 136353
    Prev
    Next
    INDEX
    Explanations

    visitors to

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

    automated rotation, csv, json, ci/cd

    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
    ያንዳ
    0.47
    workItem
    0.47
     సూ
    0.46
    编译
    0.46
    forces
    0.45
    込ま
    0.45
    quotes
    0.44
    计
    0.44
     geçmiş
    0.44
    Петер
    0.42
    POSITIVE LOGITS
     Speicher
    0.49
     Levels
    0.46
    ->$
    0.46
     Amor
    0.45
     Sponsorship
    0.44
     Gets
    0.44
     Drought
    0.43
    שו
    0.43
     Loves
    0.42
     Day
    0.42
    Activations Density 0.001%

    No Known Activations