© 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. 196109
    Prev
    Next
    INDEX
    Explanations

    employer condition

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

    block, from, etc

    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
    ه
    0.63
     آب
    0.52
    ۹
    0.50
    يين
    0.49
    */}
    0.49
    gaussian
    0.48
    ية
    0.47
    brackets
    0.47
    ේ
    0.47
     위해
    0.46
    POSITIVE LOGITS
     Conflict
    0.48
     Vial
    0.47
     Violet
    0.45
     Liu
    0.44
     Wanda
    0.43
     participates
    0.43
     Cleaning
    0.43
    uka
    0.43
     viola
    0.42
     conflicts
    0.42
    Activations Density 0.000%

    No Known Activations