© 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. 74531
    Prev
    Next
    INDEX
    Explanations

    convey Listings mesh

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

    epub, .pyc, whitelist

    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
    t
    0.52
    aile
    0.49
    elerine
    0.47
     utilizzo
    0.47
    apore
    0.47
     ಬರುತ್ತ
    0.47
     commentators
    0.46
     precepts
    0.46
     straps
    0.45
     benches
    0.45
    POSITIVE LOGITS
     sanitize
    0.46
     Rehab
    0.44
    龈
    0.43
     sass
    0.42
    卖家
    0.41
     Lego
    0.41
    也能
    0.41
    佛
    0.40
     rehab
    0.40
     μεγά
    0.39
    Activations Density 0.001%

    No Known Activations