Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 36978
    Prev
    Next
    INDEX
    Explanations

    fox, Zeppelin, red

    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
     Ve
    0.54
     Ke
    0.52
     juge
    0.51
     K
    0.51
    an
    0.50
    al
    0.48
     papal
    0.47
     D
    0.46
     anglers
    0.46
     N
    0.46
    POSITIVE LOGITS
    DriverManager
    0.44
     Theoretically
    0.43
    สวัสดี
    0.43
    磪
    0.43
     ഓഫ്
    0.42
     Stabilization
    0.42
    ourage
    0.42
     Coordinating
    0.42
    暊
    0.42
    єдна
    0.42
    Activations Density 0.000%

    No Known Activations