© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 18206
    Prev
    Next
    INDEX
    Explanations

    popular threads

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

    creating a, map; constraints are

    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
    u
    0.50
    .
    0.50
    day
    0.49
    J
    0.48
    {
    0.48
    art
    0.48
     uncomfortable
    0.48
    R
    0.48
    ULL
    0.47
    they
    0.47
    POSITIVE LOGITS
    萺
    0.53
    睗
    0.49
    LogRow
    0.49
    StartZ
    0.48
     soins
    0.48
     inverno
    0.48
    䒾
    0.47
     drawRight
    0.47
     disponibilités
    0.47
     cGraph
    0.47
    Activations Density 0.000%

    No Known Activations