© 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. 28577
    Prev
    Next
    INDEX
    Explanations

    tell me a story or information

    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
     tendered
    0.72
     нарушения
    0.70
    י
    0.68
    ک
    0.68
     glared
    0.65
    ي
    0.64
     pared
    0.63
     waved
    0.63
    y
    0.63
    ه
    0.63
    POSITIVE LOGITS
    Tell
    0.71
    Monthly
    0.63
    Directory
    0.59
     powied
    0.58
    Story
    0.57
    tellers
    0.57
    Collection
    0.56
    Management
    0.55
    Stories
    0.55
     Tells
    0.55
    Activations Density 0.050%

    No Known Activations