© 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. 14055
    Prev
    Next
    INDEX
    Explanations

    defining terms or specifying actions

    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
     pretentious
    0.48
    ).__
    0.44
     assumed
    0.44
     contradicts
    0.44
     resides
    0.43
    栊
    0.40
     cultured
    0.40
    ocrates
    0.40
    iliği
    0.40
    addContainerGap
    0.40
    POSITIVE LOGITS
    <b>
    0.52
    s
    0.52
    simple
    0.50
    Integer
    0.50
    কোন
    0.50
    Из
    0.48
    <h3>
    0.48
    CLI
    0.48
    police
    0.47
    文字列
    0.47
    Activations Density 0.008%

    No Known Activations