© 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. 50678
    Prev
    Next
    INDEX
    Explanations

    cooking and repeating actions

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

    assignment or comparison

    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
    Teri
    0.40
     liberté
    0.38
     leurs
    0.38
     görm
    0.38
    ն
    0.38
     Pipp
    0.38
    Basically
    0.36
    粼
    0.36
     bru
    0.36
     cốc
    0.36
    POSITIVE LOGITS
    再び
    0.83
     மீண்டும்
    0.79
     again
    0.77
     다시
    0.75
     ponownie
    0.73
     আবারও
    0.73
     पुन्हा
    0.71
    again
    0.70
    再度
    0.70
     снова
    0.69
    Activations Density 0.002%

    No Known Activations