© 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. 27545
    Prev
    Next
    INDEX
    Explanations

    have + past participle

    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
    ка
    0.75
    т
    0.71
    ك
    0.67
     unapolog
    0.64
     skateboarding
    0.64
    al
    0.61
     exuberant
    0.61
     а
    0.60
     इन
    0.59
     skincare
    0.59
    POSITIVE LOGITS
    是有
    0.57
    اس
    0.55
    inx
    0.54
     been
    0.54
    uje
    0.54
    ě
    0.54
    ?
    0.53
    pw
    0.53
    是一
    0.52
    ws
    0.52
    Activations Density 0.012%

    No Known Activations