© 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. 12034
    Prev
    Next
    INDEX
    Explanations

    text arrangement

    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
     Electricity
    0.46
    Electricity
    0.42
    🤟
    0.42
     تل
    0.41
     Electrical
    0.39
     Contents
    0.39
     aun
    0.39
     بمن
    0.38
     ಗ
    0.38
     alo
    0.38
    POSITIVE LOGITS
    ה
    0.46
     spinner
    0.44
    spinner
    0.43
    รรม
    0.43
     concludes
    0.41
    carousel
    0.41
    რულ
    0.41
    astikan
    0.41
    erreur
    0.40
     vecteur
    0.40
    Activations Density 0.000%

    No Known Activations