© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 50743
    Prev
    Next
    INDEX
    Explanations

    safety requirement

    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
     څرنګوالی
    0.45
    Forest
    0.44
    掝
    0.44
    كم
    0.44
    樂
    0.44
     שמ
    0.43
    动力
    0.42
     Lösungen
    0.42
     وك
    0.42
    机
    0.42
    POSITIVE LOGITS
    acon
    0.48
     extensively
    0.48
     being
    0.48
     xe
    0.48
     excessively
    0.48
     tense
    0.47
    ocycl
    0.47
    ک
    0.47
     dialect
    0.47
     beautifully
    0.46
    Activations Density 0.001%

    No Known Activations