© 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. 31626
    Prev
    Next
    INDEX
    Explanations

    programming, math, or sequence contexts

    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
    赚钱
    0.47
    🙎
    0.40
     Polytechnic
    0.40
    dotnet
    0.40
    如果不
    0.38
     apakah
    0.38
    лаве
    0.38
    现代化
    0.38
    减肥
    0.37
    બર
    0.37
    POSITIVE LOGITS
     beiden
    0.43
     homeomorphism
    0.42
    motionProxy
    0.42
    +{
    0.41
    ުގައި
    0.41
    ('['
    0.41
     strokeWeight
    0.41
     Sasaki
    0.41
    <td>
    0.39
     warp
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.