© 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. 41954
    Prev
    Next
    INDEX
    Explanations

    charge all, formula results, find kangaroos

    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
    論文
    0.43
    ौदा
    0.42
    antiated
    0.41
    医師
    0.39
    уда
    0.38
    潅
    0.38
    人数
    0.38
    ুর
    0.37
    glycos
    0.37
    orneys
    0.37
    POSITIVE LOGITS
     backlight
    0.60
     effekt
    0.52
     illumination
    0.50
     illuminate
    0.50
     aerodynamic
    0.50
     இங்கே
    0.50
     accessoires
    0.49
     oiseaux
    0.49
     used
    0.48
     lighting
    0.48
    Activations Density 0.007%

    No Known Activations