© 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. 91760
    Prev
    Next
    INDEX
    Explanations

    tap, Park, believing, schedule, tab

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

    social media ad

    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
     Color
    0.46
    ξει
    0.46
    ไหล
    0.44
     inglesa
    0.42
    質
    0.41
    ൃത്ത
    0.40
    욀
    0.40
     Shropshire
    0.40
     Lit
    0.39
    质
    0.39
    POSITIVE LOGITS
     to
    0.62
     использование
    0.48
     agnostic
    0.48
     consci
    0.48
     outage
    0.47
     භාවිත
    0.47
     at
    0.47
     almacenamiento
    0.47
     invent
    0.46
     తీసుకొ
    0.46
    Activations Density 0.000%

    No Known Activations