© 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. 111493
    Prev
    Next
    INDEX
    Explanations

    sql group by clauses

    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
    code
    0.50
    Game
    0.49
    Party
    0.48
    违反
    0.47
    代码
    0.46
    Codes
    0.45
    Betty
    0.45
    语
    0.45
    fatal
    0.45
    left
    0.45
    POSITIVE LOGITS
     pancreatic
    0.53
    ਨ
    0.51
     angiogenic
    0.50
     servants
    0.49
     anggota
    0.48
     enh
    0.47
     anthropogenic
    0.47
     pikiran
    0.47
     Cappadocia
    0.47
     polypeptides
    0.46
    Activations Density 0.003%

    No Known Activations