© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 205318
    Prev
    Next
    INDEX
    Explanations

    caption numbers and code

    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
     منٹو
    0.52
    <?=
    0.41
    تاریخ
    0.41
    ο
    0.40
     Licht
    0.39
    レール
    0.38
     luz
    0.38
    Integrating
    0.38
    𝔬
    0.38
     gelt
    0.38
    POSITIVE LOGITS
    estion
    0.46
     ток
    0.39
    ದುಕೊಳ್ಳ
    0.38
     пред
    0.38
     കൂട്ട
    0.38
     defensive
    0.37
     pneumatic
    0.36
    >**
    0.36
     telescopic
    0.36
     searches
    0.36
    Activations Density 0.005%

    No Known Activations