© 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. 200330
    Prev
    Next
    INDEX
    Explanations

    pattern detection

    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
     functionally
    0.54
     機能
    0.48
     функциона
    0.47
    疃
    0.47
     Bitt
    0.46
     ಸಿ
    0.46
     funcional
    0.45
     funkc
    0.45
     реа
    0.45
     ቤ
    0.44
    POSITIVE LOGITS
    emann
    0.45
     Scottish
    0.43
     düşün
    0.42
     whereof
    0.42
     rue
    0.41
     presso
    0.41
    ibo
    0.41
    ною
    0.41
     জানিয়ে
    0.41
    ώ
    0.41
    Activations Density 0.004%

    No Known Activations