© 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. 31-GEMMASCOPE-2-RES-262K
    7. 71326
    Prev
    Next
    INDEX
    Explanations

    definitions and continuations

    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_31_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
    ان
    0.50
     autorización
    0.44
    各种
    0.43
     ugy
    0.43
     التجارية
    0.42
     commerciales
    0.42
    ໄ
    0.41
     각종
    0.41
     పు
    0.41
    èdent
    0.41
    POSITIVE LOGITS
     Workbench
    0.42
    iforn
    0.38
     somewhat
    0.37
    TeX
    0.37
    ee
    0.37
    undance
    0.37
    eth
    0.37
    ཎ
    0.37
    ul
    0.37
     tend
    0.37
    Activations Density 0.003%

    No Known Activations