© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 84687
    Prev
    Next
    INDEX
    Explanations

    spotted patterns and colors

    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
    ۇ
    0.44
     इन्वेस्टमेंट
    0.44
     المستخدم
    0.41
    orifice
    0.38
     الشعر
    0.37
     hexagonal
    0.36
     করণ
    0.36
     sør
    0.36
    SOR
    0.36
    秃
    0.36
    POSITIVE LOGITS
     Kind
    0.41
    uell
    0.39
     Sunlight
    0.37
     Guides
    0.37
     Bertrand
    0.37
     Mother
    0.36
     Moy
    0.36
     Colors
    0.36
     இன்னொரு
    0.35
    odend
    0.35
    Activations Density 0.000%

    No Known Activations