© 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. 66779
    Prev
    Next
    INDEX
    Explanations

    cost, returns, purchased, tires, settings, album, apply, float

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

    directory, images, and RNA interactions

    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
    -
    0.55
    olution
    0.52
    an
    0.52
    +
    0.50
    case
    0.49
    o
    0.49
    form
    0.48
    order
    0.48
    er
    0.47
    i
    0.47
    POSITIVE LOGITS
     sparsim
    0.54
     reciprocating
    0.52
     delim
    0.49
     freg
    0.48
     fnt
    0.48
     theseKeys
    0.47
     ቦታ
    0.47
     fifties
    0.46
     スポーツ
    0.46
     tę
    0.46
    Activations Density 0.000%

    No Known Activations