© 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. 99260
    Prev
    Next
    INDEX
    Explanations

    regional competition

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

    involved in processes and communication

    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
    Ui
    0.57
    CO
    0.55
    OAuth
    0.55
    HT
    0.54
    消費
    0.54
    И
    0.54
    DF
    0.54
    UD
    0.54
    Thrown
    0.54
    О
    0.54
    POSITIVE LOGITS
    阌
    0.47
     כאשר
    0.44
     भय
    0.43
     maga
    0.43
    icch
    0.42
     olen
    0.42
    兹
    0.41
     मग
    0.40
     საერთ
    0.40
    rupa
    0.40
    Activations Density 0.001%

    No Known Activations