© 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. 143680
    Prev
    Next
    INDEX
    Explanations

    ESM, Node.js, configuration

    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
    痙
    0.48
    ）』
    0.47
    ጤ
    0.46
    omized
    0.45
    ur
    0.44
     अनावश्यक
    0.42
    ine
    0.42
    hen
    0.41
    feit
    0.41
    rab
    0.41
    POSITIVE LOGITS
     selves
    0.48
     celulares
    0.46
     ދ
    0.44
     azules
    0.43
     Self
    0.42
     város
    0.42
     royals
    0.42
     relatos
    0.42
     comuni
    0.41
     solvents
    0.41
    Activations Density 0.010%

    No Known Activations