© 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. 124284
    Prev
    Next
    INDEX
    Explanations

    opinions, race, businesses, thoughts, game

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

    legitimate creators, beautiful frescoes

    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
    ς
    0.52
     aphids
    0.50
    ség
    0.48
    სი
    0.46
     êtes
    0.46
     épais
    0.45
     双
    0.45
     assistants
    0.45
    ों
    0.45
     reefs
    0.45
    POSITIVE LOGITS
    atham
    0.46
    ロ
    0.45
     bladder
    0.44
    ure
    0.43
    cluded
    0.43
     harmon
    0.43
    വദ
    0.43
    had
    0.43
    hematic
    0.42
    velocityY
    0.41
    Activations Density 0.000%

    No Known Activations