© 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. 181655
    Prev
    Next
    INDEX
    Explanations

    south or north

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

    stereotypes, sympathetic, anxiety

    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
    isLen
    0.49
    績
    0.49
    accomp
    0.48
    ونکي
    0.47
    LECTION
    0.47
    лек
    0.46
    كينا
    0.46
     பெண்க
    0.45
    PosY
    0.45
    hovah
    0.45
    POSITIVE LOGITS
     UPDATE
    0.52
     I
    0.51
     volatility
    0.51
     Anxiety
    0.51
     anxiety
    0.49
    ӣ
    0.49
     Temperature
    0.48
    ̣i
    0.48
     update
    0.47
     Updating
    0.47
    Activations Density 0.000%

    No Known Activations