© 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. 31-GEMMASCOPE-2-RES-262K
    4. 28675
    Prev
    Next
    INDEX
    Explanations

    game scores and updates

    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
     august
    0.39
     knees
    0.37
     tropics
    0.37
    sendPluginResult
    0.37
    .]
    0.37
     piernas
    0.37
     matemat
    0.36
    Totals
    0.36
    쿰
    0.36
    飢
    0.36
    POSITIVE LOGITS
     बि
    0.38
     当然
    0.38
     Another
    0.37
    当然
    0.35
    vist
    0.35
    Aaj
    0.35
    鹊
    0.34
     व्यावसायिक
    0.34
     নিরাপদ
    0.34
     परिचालन
    0.33
    Activations Density 0.001%

    No Known Activations