© 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. 190550
    Prev
    Next
    INDEX
    Explanations

    rules or requirements

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

    technical errors and specific actions

    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
    اسية
    0.54
     느끼
    0.47
    dropna
    0.46
    arrivée
    0.45
     Стаўкі
    0.45
    ㄨ
    0.45
    валися
    0.45
     Abou
    0.44
    崤
    0.44
    結晶
    0.44
    POSITIVE LOGITS
    ;
    0.48
     —
    0.46
     aptly
    0.46
     as
    0.46
    T
    0.45
     внеш
    0.45
     touted
    0.44
     брен
    0.44
    ਬਰ
    0.44
     alluded
    0.44
    Activations Density 0.001%

    No Known Activations