© 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. 69745
    Prev
    Next
    INDEX
    Explanations

    basement floors

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

    Byzantine surcharge digit

    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
    っております
    0.49
    كتور
    0.49
    酤
    0.48
    的游戏
    0.47
    âte
    0.47
     betreff
    0.45
    ็น
    0.45
    aterra
    0.45
    ivale
    0.45
    悸
    0.45
    POSITIVE LOGITS
    sk
    0.56
     DOG
    0.54
     on
    0.54
     around
    0.53
    an
    0.52
     SO
    0.51
    3
    0.51
     or
    0.50
     DO
    0.50
     AX
    0.50
    Activations Density 0.000%

    No Known Activations