© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 124128
    Prev
    Next
    INDEX
    Explanations

    haiku about

    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
     interrupting
    0.52
     ultraf
    0.49
     arist
    0.47
    teddy
    0.46
    뻣
    0.46
     patriots
    0.45
     exemptions
    0.45
     aprovechar
    0.45
     nitidus
    0.44
     wrenches
    0.44
    POSITIVE LOGITS
    规则
    0.43
    界
    0.41
    εκ
    0.41
    牖
    0.40
    单元
    0.40
    적으로
    0.40
    ತಿ
    0.40
    rizione
    0.40
    ψη
    0.39
    ٖ
    0.38
    Activations Density 0.005%

    No Known Activations