© 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. 53046
    Prev
    Next
    INDEX
    Explanations

    Porsche

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

    expecting only death

    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
    モ
    0.50
    ラ
    0.49
    のお客様
    0.48
    με
    0.47
    親子
    0.47
    ボ
    0.46
    κα
    0.46
    메
    0.46
     momentos
    0.46
    カ
    0.46
    POSITIVE LOGITS
    äll
    0.50
    angerschaft
    0.48
    ücksicht
    0.46
    ithmetic
    0.45
    thal
    0.44
     Necessity
    0.44
    Setpoint
    0.44
    дян
    0.44
    apsack
    0.44
    ssä
    0.44
    Activations Density 0.000%

    No Known Activations