© 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. 31-GEMMASCOPE-2-RES-262K
    7. 123807
    Prev
    Next
    INDEX
    Explanations

    diagrams of data flow

    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
    硖
    0.38
    กร
    0.37
    也都
    0.36
    所谓的
    0.36
    ewnątrz
    0.36
     உட
    0.35
     Manuscript
    0.35
     zp
    0.35
    那里
    0.34
     प्रिंसिपल
    0.34
    POSITIVE LOGITS
     destru
    0.50
     soluciones
    0.48
    خستان
    0.48
     sozinho
    0.47
    ዔ
    0.47
     casework
    0.46
     অনুষ্ঠ
    0.46
    ورية
    0.46
     phasing
    0.46
    ᙱ
    0.46
    Activations Density 0.004%

    No Known Activations