© 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. 21445
    Prev
    Next
    INDEX
    Explanations

    updates, status, lyrics, vocals, review, kits, date

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

    column names

    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
    lamp
    0.41
    OG
    0.37
    Flask
    0.37
    BS
    0.36
     damping
    0.35
     ){
    0.34
    。
    0.34
    raspberry
    0.34
    🏿
    0.34
    What
    0.34
    POSITIVE LOGITS
     अवेलेबल
    0.41
     कराने
    0.40
     matchup
    0.39
     इनको
    0.39
    になって
    0.38
     dólares
    0.38
    了起来
    0.38
     Ihres
    0.38
     você
    0.38
     champs
    0.38
    Activations Density 0.001%

    No Known Activations