© 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. 46450
    Prev
    Next
    INDEX
    Explanations

    third, fake, board, auto

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

    making only, concentration, sound echoes

    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
     regulate
    0.54
     synthesize
    0.51
     '}';
    0.51
    觐
    0.50
    <unused1751>
    0.50
     collaborate
    0.48
    解释
    0.47
    tochy
    0.47
    ដែរ
    0.47
    释
    0.47
    POSITIVE LOGITS
    seconds
    0.56
     After
    0.50
    td
    0.48
    нта
    0.44
    third
    0.43
    tier
    0.42
     первого
    0.42
    は
    0.42
    desc
    0.42
     ሲ
    0.42
    Activations Density 0.000%

    No Known Activations