© 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. 5380
    Prev
    Next
    INDEX
    Explanations

    beginning with or accompanying

    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
     بۆ
    0.41
     وذلك
    0.36
     ಜನ
    0.33
    لیفون
    0.33
     곳
    0.32
     እስ
    0.31
    来源
    0.31
    ordu
    0.30
    來源
    0.30
     }()
    0.30
    POSITIVE LOGITS
     with
    0.84
     dengan
    0.84
     với
    0.78
     avec
    0.77
    dengan
    0.71
    with
    0.66
     עם
    0.63
    ជាមួយនឹង
    0.63
     unscathed
    0.63
     without
    0.59
    Activations Density 0.098%

    No Known Activations