© 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-65K
    7. 16987
    Prev
    Next
    INDEX
    Explanations

    programming contexts

    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_65k_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
    ਮ
    0.52
    yii
    0.46
    𝒔
    0.46
     instalado
    0.45
     Yii
    0.44
    𝒗
    0.43
    𝗽
    0.42
     खड़े
    0.42
    𝚢
    0.42
     පි
    0.42
    POSITIVE LOGITS
     straws
    0.45
     curricula
    0.42
     amendments
    0.42
     Amendments
    0.41
     gymnastics
    0.40
     assessments
    0.40
     deont
    0.39
    jLabel
    0.39
     grammar
    0.39
    setOnAction
    0.39
    Activations Density 0.000%

    No Known Activations