© 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. 134650
    Prev
    Next
    INDEX
    Explanations

    states, actions, or entities

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

    explaining specific concepts

    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
     Puri
    0.51
     話
    0.47
     intelligents
    0.46
     fáb
    0.45
     {{{
    0.45
     puja
    0.44
     pyar
    0.44
     FRIED
    0.44
     Istanbul
    0.44
     〈
    0.44
    POSITIVE LOGITS
    ่
    0.47
    じん
    0.43
    ิน
    0.43
     والش
    0.43
    𝑏
    0.43
    ინი
    0.42
    الت
    0.42
     ochrony
    0.42
    rement
    0.42
    œil
    0.41
    Activations Density 0.000%

    No Known Activations