© 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. 110137
    Prev
    Next
    INDEX
    Explanations

    time, title, weeds, nothing

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

    declaring faith or religious statements

    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
    <0x98>
    0.51
    विरो
    0.50
    کو
    0.48
     ‘
    0.46
    тини
    0.46
     ignoring
    0.45
    合った
    0.45
    न
    0.45
    ন
    0.44
    xml
    0.44
    POSITIVE LOGITS
    deki
    0.48
     Puja
    0.46
     സാധ
    0.45
     रोजाना
    0.44
     semanal
    0.44
    屶
    0.44
     Bunun
    0.43
     gde
    0.43
     美術
    0.42
     பகுதிக
    0.42
    Activations Density 0.003%

    No Known Activations