© 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. 194458
    Prev
    Next
    INDEX
    Explanations

    surgery, Rustic, supervisor, designed, coins

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

    tailor explanation to user level

    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
    مة
    0.44
     SELECTED
    0.43
    ف
    0.43
    zzi
    0.41
     Privat
    0.41
     EST
    0.39
    苄
    0.38
     WALTER
    0.38
     impug
    0.38
     organism
    0.37
    POSITIVE LOGITS
    wheeled
    0.53
     Hota
    0.51
     mouthpiece
    0.51
     scena
    0.50
     gimbal
    0.50
     ļ
    0.50
     beanie
    0.49
     tabela
    0.49
     Terminator
    0.48
     sweatshirt
    0.48
    Activations Density 0.000%

    No Known Activations