© 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. 31-GEMMASCOPE-2-RES-262K
    7. 20532
    Prev
    Next
    INDEX
    Explanations

    starting points, sequence, or initial items

    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
    也
    0.42
     ھ
    0.37
    ッ
    0.37
     مهم
    0.36
    LEXPORT
    0.36
    迠
    0.36
     amenazas
    0.35
     infine
    0.35
    ֖
    0.35
    insuff
    0.35
    POSITIVE LOGITS
     Öncelikle
    0.41
     প্রথমেই
    0.39
     ಈಗಾಗಲೇ
    0.36
     অথচ
    0.34
    ুকের
    0.33
    кових
    0.32
    ರಿಸಿ
    0.31
    кової
    0.31
    만을
    0.31
    どのような
    0.30
    Activations Density 0.056%

    No Known Activations