© 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. 239531
    Prev
    Next
    INDEX
    Explanations

    common phrases and items

    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
     Pal
    0.45
     Confederate
    0.45
    б
    0.42
    <thead>
    0.41
     Iron
    0.40
     λειτουργ
    0.40
    ub
    0.40
     į
    0.39
     επι
    0.39
    γχ
    0.39
    POSITIVE LOGITS
    서는
    0.50
    쾨
    0.47
    शीर
    0.46
     weddings
    0.45
    diamonds
    0.45
     pods
    0.44
    राजस्थान
    0.44
    隐含规则
    0.44
    စား
    0.43
    フライ
    0.43
    Activations Density 0.001%

    No Known Activations