© 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. 168591
    Prev
    Next
    INDEX
    Explanations

    function with, occurs, threat might, batch of

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

    Rust, pathway, nicht, whis

    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
     多く
    0.56
     OFFIC
    0.55
    ς
    0.52
     PARTY
    0.50
    s
    0.48
     CAPITAL
    0.46
     AFRICA
    0.46
    ’;
    0.45
     Party
    0.44
     મોટી
    0.44
    POSITIVE LOGITS
     invariants
    0.49
    Acrylic
    0.48
    🟢
    0.48
    فون
    0.45
    内心
    0.44
    😒
    0.44
     arn
    0.44
     جست
    0.44
    😅
    0.43
    веден
    0.43
    Activations Density 0.000%

    No Known Activations