© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 11057
    Prev
    Next
    INDEX
    Explanations

    module.exports definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ORTYPE
    0.45
    自体
    0.42
     էր
    0.41
     clearContext
    0.40
     thoracique
    0.39
    ौरा
    0.38
    仙台
    0.38
    ᒐ
    0.38
    缦
    0.38
     headwinds
    0.38
    POSITIVE LOGITS
     Pug
    0.44
     Havre
    0.42
    social
    0.41
    evidence
    0.41
    generation
    0.40
     Pok
    0.39
    ()=>{
    0.39
     membentuk
    0.39
     Secretary
    0.39
    infl
    0.39
    Activations Density 0.000%

    No Known Activations