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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 15562
    Prev
    Next
    INDEX
    Explanations

    ethical, reliable, transparent, compliant

    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
    シンプル
    0.32
    악
    0.30
     emphatically
    0.30
     عجیب
    0.30
     elegance
    0.30
    ख्यात
    0.29
    激烈
    0.29
    complexity
    0.29
     slecht
    0.29
    <unused70>
    0.29
    POSITIVE LOGITS
     könnte
    0.35
     poate
    0.34
     have
    0.32
    стройства
    0.32
    ियो
    0.31
     może
    0.31
     petrol
    0.31
     मिलेंगे
    0.30
    রাস
    0.30
     기타
    0.30
    Activations Density 0.007%

    No Known Activations