© 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. 128640
    Prev
    Next
    INDEX
    Explanations

    requirements, procedures, and time

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

    numbers and specific entities

    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
    itze
    0.49
    ੰਜ
    0.48
    𝘐
    0.47
     desenho
    0.46
    الش
    0.46
    แต่ละ
    0.45
    encils
    0.45
    ozo
    0.45
    uno
    0.45
    Ց
    0.44
    POSITIVE LOGITS
     online
    0.47
     hundred
    0.46
     মিশ
    0.44
     Coachella
    0.44
     н
    0.43
     Texas
    0.42
     experts
    0.42
     maim
    0.42
     perpetuity
    0.42
     bestselling
    0.42
    Activations Density 0.000%

    No Known Activations