© 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. 131612
    Prev
    Next
    INDEX
    Explanations

    where introducing definitions

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

    introduces clarifying clauses

    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
     einiger
    0.43
     Seja
    0.42
    هما
    0.41
    sqlalchemy
    0.41
     einz
    0.41
    ၍
    0.41
     encomendas
    0.40
     asta
    0.39
     zwei
    0.39
    حده
    0.39
    POSITIVE LOGITS
     circumferential
    0.47
    elines
    0.43
     개념
    0.42
     간
    0.42
     прости
    0.42
    eline
    0.41
     መጠቀም
    0.41
    縝
    0.41
    唏
    0.40
    ँच
    0.40
    Activations Density 0.000%

    No Known Activations