© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 224891
    Prev
    Next
    INDEX
    Explanations

    enter jurisdictions boundaries

    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_40_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
    Woman
    0.40
     LGB
    0.40
     sante
    0.39
     woman
    0.38
     gastron
    0.38
    راب
    0.38
    हार्
    0.38
    靠
    0.38
     foodie
    0.37
     BM
    0.37
    POSITIVE LOGITS
    rcode
    0.43
    ジング
    0.38
     bytecode
    0.38
    LayoutInflater
    0.37
    ṓ
    0.37
    轳
    0.37
     adapts
    0.36
     Erschein
    0.36
     थोडे
    0.35
     స్థాయి
    0.35
    Activations Density 0.001%

    No Known Activations