© 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. 16967
    Prev
    Next
    INDEX
    Explanations

    recent introductions

    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
    ρε
    0.41
    ligi
    0.41
    ㄑ
    0.41
    baseHP
    0.40
    是一家
    0.40
    Сейчас
    0.40
     tetahi
    0.39
    樸
    0.39
    李
    0.39
     wskaz
    0.38
    POSITIVE LOGITS
     new
    0.91
     এবারের
    0.89
     nieuwe
    0.88
    这一次
    0.87
     unprecedented
    0.86
     nuove
    0.86
     neue
    0.85
     again
    0.84
    新的
    0.84
     neuen
    0.82
    Activations Density 0.281%

    No Known Activations