© 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. 4929
    Prev
    Next
    INDEX
    Explanations

    purpose or benefit

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

    purpose for

    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
     Martín
    0.14
     tetahi
    0.14
    ları
    0.13
     bụ
    0.12
    Ą
    0.12
     stesso
    0.12
     pezzi
    0.12
     た
    0.12
    Necessary
    0.12
    ือน
    0.12
    POSITIVE LOGITS
    pping
    0.21
    для
    0.19
     combating
    0.18
    สำหรับการ
    0.18
     prioritizing
    0.17
    in
    0.17
    untuk
    0.17
     facilitate
    0.17
     facilitating
    0.17
     furthering
    0.17
    Activations Density 0.786%

    No Known Activations