© 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. 4972
    Prev
    Next
    INDEX
    Explanations

    a large language model

    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
    7
    0.45
    8
    0.42
    9
    0.41
     dashes
    0.39
    Л
    0.37
    К
    0.36
    רג
    0.35
    a
    0.34
    an
    0.33
    Н
    0.33
    POSITIVE LOGITS
     মধ্যে
    0.42
     แต่
    0.41
     મુખ્ય
    0.41
    
    0.40
     ध्वस्त
    0.40
     आदी
    0.40
    <unused713>
    0.39
     ஒப்பந்த
    0.39
    <unused669>
    0.39
    <unused706>
    0.39
    Activations Density 0.059%

    No Known Activations