© 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. 16-GEMMASCOPE-2-RES-262K
    7. 40683
    Prev
    Next
    INDEX
    Explanations

    president, girl

    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_16_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
    ↵↵
    0.61
    ter
    0.57
    ort
    0.55
    ↵↵↵
    0.52
    當時
    0.51
    َف
    0.49
    分页
    0.49
    QUOTE
    0.48
     determinant
    0.47
     Satz
    0.47
    POSITIVE LOGITS
     в
    0.60
    5
    0.60
    ваются
    0.57
     tomorrow
    0.57
     ваше
    0.57
     мечта
    0.56
     пе
    0.55
    वासियों
    0.55
    कांच्या
    0.55
     e
    0.54
    Activations Density 0.000%

    No Known Activations