© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 41418
    Prev
    Next
    INDEX
    Explanations

    These results and same

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

    business concepts and operations

    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
     জায়গা
    0.46
     குறிப்பிடத்தக்க
    0.45
     molded
    0.44
     ಸುದ್ದ
    0.44
    ırmızı
    0.44
    ۷
    0.44
    <0x07>
    0.42
    🏵
    0.42
    osas
    0.42
     obscured
    0.42
    POSITIVE LOGITS
    ੰ
    0.47
    ненко
    0.46
     îles
    0.46
    чет
    0.45
     Rajesh
    0.44
     destinés
    0.43
    angular
    0.43
    NgModule
    0.43
    ظم
    0.43
    ченный
    0.43
    Activations Density 0.000%

    No Known Activations