© 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. 235204
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     cuero
    0.41
    骷
    0.40
    મારા
    0.40
    ≻
    0.40
    κού
    0.39
    淖
    0.39
    㖘
    0.39
     hierro
    0.38
     tytu
    0.38
    潇
    0.38
    POSITIVE LOGITS
    oid
    0.40
     matching
    0.39
     rev
    0.39
     Accounting
    0.38
     category
    0.38
     revival
    0.37
     restorative
    0.37
     top
    0.37
     accounting
    0.37
     tops
    0.37
    Activations Density 0.001%

    No Known Activations