© 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. 113158
    Prev
    Next
    INDEX
    Explanations

    concerning those, page of, beyond the, any page, stopped selling, approaching hazardous

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

    some conditions or requirements

    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
    waitSeconds
    0.50
     કાર્યવાહી
    0.47
    fieldContext
    0.46
     प्यारा
    0.44
    ड़ी
    0.43
     समर्
    0.43
    터
    0.43
     화
    0.43
     parameterType
    0.43
     principalColumn
    0.43
    POSITIVE LOGITS
     to
    0.47
     გახ
    0.46
     fluv
    0.45
    Qr
    0.44
     be
    0.44
     Pá
    0.43
     DME
    0.43
     kte
    0.43
     adopt
    0.42
     verwand
    0.42
    Activations Density 0.002%

    No Known Activations