© 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. 15497
    Prev
    Next
    INDEX
    Explanations

    actions and concepts

    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
    ὸ
    0.44
    梟
    0.38
    ریب
    0.38
     perturbed
    0.37
    abies
    0.37
    ாவின்
    0.36
    აციის
    0.36
    esecuzione
    0.36
     Polymer
    0.36
     Schilling
    0.36
    POSITIVE LOGITS
     태
    0.46
     և
    0.46
     nozzles
    0.46
     ú
    0.46
     collect
    0.43
     jas
    0.43
     indépend
    0.43
     ডকুমেন্ট
    0.43
     جمعه
    0.42
     wetensch
    0.42
    Activations Density 4.894%

    No Known Activations