© 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. 2043
    Prev
    Next
    INDEX
    Explanations

    movement and transit

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

    documentation and code

    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
    Net
    0.49
     Lad
    0.47
    Markets
    0.47
     poate
    0.46
    相談
    0.46
    ราคา
    0.46
     больше
    0.45
    ")}
    0.45
     tamu
    0.45
    Bola
    0.45
    POSITIVE LOGITS
     Zeitschrift
    0.52
    un
    0.51
    m
    0.51
    ur
    0.50
    arg
    0.50
    uva
    0.49
    redirect
    0.48
     reverses
    0.47
     संस्कृत
    0.47
    ⎥
    0.47
    Activations Density 0.000%

    No Known Activations