© 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. 243387
    Prev
    Next
    INDEX
    Explanations

    purchase from

    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
    s
    0.55
    ন্তা
    0.53
    मानी
    0.50
     알
    0.48
    ו
    0.48
    տր
    0.48
    有名な
    0.47
    ের
    0.47
    銭
    0.47
    きる
    0.46
    POSITIVE LOGITS
     rhinoceros
    0.46
    inder
    0.46
     {}
    0.46
     rhod
    0.46
    িল
    0.45
    jes
    0.45
    Ik
    0.45
     discoveries
    0.44
    nyder
    0.43
    িলের
    0.43
    Activations Density 0.001%

    No Known Activations