© 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. 40-GEMMASCOPE-2-RES-262K
    7. 133851
    Prev
    Next
    INDEX
    Explanations

    dot or point

    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_40_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
     peaches
    0.43
     ropes
    0.42
     trophies
    0.41
     coils
    0.40
    êmes
    0.40
     yarns
    0.40
     spazio
    0.40
    🏺
    0.39
    曙
    0.38
    🍠
    0.37
    POSITIVE LOGITS
     dot
    1.95
     dots
    1.80
    Dot
    1.64
     Dot
    1.63
    dot
    1.63
    dots
    1.49
     Dots
    1.46
    Dots
    1.41
     DOT
    1.34
    DOT
    1.31
    Activations Density 0.052%

    No Known Activations