© 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. 15498
    Prev
    Next
    INDEX
    Explanations

    LaTeX packages

    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
     mannit
    0.41
     geomet
    0.40
     geometría
    0.40
     variétés
    0.39
     لائن
    0.38
    䍧
    0.38
    ’
    0.38
     geometry
    0.38
     inFile
    0.38
    geometry
    0.38
    POSITIVE LOGITS
    🟢
    0.38
     trims
    0.37
     planes
    0.35
     ducks
    0.35
     దో
    0.34
     WeChat
    0.34
     tune
    0.34
     j
    0.34
     Hone
    0.34
    ESG
    0.34
    Activations Density 0.000%

    No Known Activations