© 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. 15505
    Prev
    Next
    INDEX
    Explanations

    sum types

    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
    पृ
    0.39
    равни
    0.39
    akarane
    0.38
     parallèles
    0.37
    zones
    0.37
    䡆
    0.37
    lens
    0.37
    堣
    0.36
     التيار
    0.36
    ള്ള
    0.36
    POSITIVE LOGITS
     Supplements
    0.54
     supplements
    0.53
     Pill
    0.52
     Foods
    0.45
     Best
    0.45
     erectile
    0.44
     rhino
    0.44
     CBD
    0.44
     niacin
    0.43
     pills
    0.43
    Activations Density 0.000%

    No Known Activations