© 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. 138431
    Prev
    Next
    INDEX
    Explanations

    maintaining or selling issues

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

    bouncy beat

    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
     bearings
    0.47
    :
    0.46
     cosmet
    0.45
    \
    0.44
     trainees
    0.44
     tools
    0.44
     benign
    0.44
     collectibles
    0.43
     clichés
    0.43
     superstars
    0.42
    POSITIVE LOGITS
     옛
    0.55
     Dengan
    0.51
     형태로
    0.51
    秞
    0.49
    Categorie
    0.48
     형태
    0.47
     معكم
    0.46
     இதன்
    0.46
    TransactionLog
    0.46
     आकार
    0.46
    Activations Density 0.000%

    No Known Activations