© 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. 22417
    Prev
    Next
    INDEX
    Explanations

    purchases made

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

    products and advertising

    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
     AMPK
    0.49
     وي
    0.48
    Ꮎ
    0.44
    ман
    0.44
    ウ
    0.43
     mantenimiento
    0.43
     thả
    0.43
     probablement
    0.42
     Ω
    0.42
     quyển
    0.42
    POSITIVE LOGITS
     advertiser
    0.46
    笨
    0.46
    iben
    0.44
    RAC
    0.44
    ிலும்
    0.43
     parody
    0.43
    rici
    0.42
    ຜະລິດຕະພັນ
    0.42
    Media
    0.42
    innis
    0.42
    Activations Density 0.001%

    No Known Activations