© 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-3-270M-IT
    5. 15-GEMMASCOPE-2-RES-262K
    7. 69587
    Prev
    Next
    INDEX
    Explanations

    Progression

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_15_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
     zoos
    1.38
     snorkel
    1.38
    cinas
    1.38
    odont
    1.37
    蠣
    1.35
     dodge
    1.34
     conveying
    1.30
     Broch
    1.28
    spam
    1.27
    fon
    1.24
    POSITIVE LOGITS
    紅色
    1.67
     ανάπτυ
    1.63
    飪
    1.63
     δρα
    1.58
    为
    1.58
    感到
    1.55
     amiga
    1.55
     experience
    1.55
    irti
    1.53
    每一個
    1.53
    Activations Density 0.001%

    No Known Activations