© 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. 178937
    Prev
    Next
    INDEX
    Explanations

    considerations may

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

    patch changes, HPV, API access

    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
    <!
    0.47
    CAR
    0.47
    BOLD
    0.47
    COMING
    0.46
    inic
    0.45
    LAND
    0.45
    WITH
    0.44
     ॥
    0.44
     இடையே
    0.44
     smer
    0.44
    POSITIVE LOGITS
    ኛው
    0.47
    лика
    0.46
     ство
    0.46
     Университе
    0.46
    ಟ್
    0.45
     চৈতন্যের
    0.44
     Knicks
    0.44
     judiciales
    0.44
     ヴィ
    0.44
     attham
    0.43
    Activations Density 0.000%

    No Known Activations