© 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. 5738
    Prev
    Next
    INDEX
    Explanations

    corporations and legal professionals

    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
     quirks
    0.38
    ेच्छा
    0.35
    🔨
    0.34
     गुस्से
    0.34
     idiots
    0.33
     ballads
    0.33
     regex
    0.33
     ridiculous
    0.32
    😩
    0.31
    😡
    0.31
    POSITIVE LOGITS
     ООО
    0.39
     partnering
    0.37
     مسئول
    0.37
    株式会社
    0.37
    partner
    0.35
     partner
    0.35
    Partner
    0.35
     партнер
    0.34
     spokesperson
    0.34
     Corporation
    0.33
    Activations Density 0.034%

    No Known Activations