© 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. 20062
    Prev
    Next
    INDEX
    Explanations

    file path and input

    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
    生产
    0.33
     stage
    0.33
     modules
    0.33
     features
    0.31
     feature
    0.31
     lợi
    0.31
     ​​
    0.31
     salas
    0.31
    好きな
    0.31
     scripting
    0.30
    POSITIVE LOGITS
    ковым
    0.37
     സാഹചര്യ
    0.36
     ලද
    0.36
     }}=
    0.36
    敉
    0.36
     фараз
    0.35
    nytimes
    0.34
    店の
    0.34
     যেহেতু
    0.33
    URNIZOR
    0.33
    Activations Density 0.188%

    No Known Activations