© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 190725
    Prev
    Next
    INDEX
    Explanations

    distinguishing current states

    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_40_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
     চৈতন্যের
    0.41
     مریض
    0.40
    캣
    0.39
    茆
    0.39
     क्रिकेट
    0.38
     ক্রিকেট
    0.38
     Checker
    0.38
     Tym
    0.37
     Tregs
    0.37
    鹫
    0.36
    POSITIVE LOGITS
    編
    0.42
     MAINTENANCE
    0.41
     EU
    0.39
     clip
    0.39
    rás
    0.38
     replay
    0.38
    ency
    0.38
     आपने
    0.38
    ต่อ
    0.38
     fontSize
    0.37
    Activations Density 0.000%

    No Known Activations