© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 83686
    Prev
    Next
    INDEX
    Explanations

    login username and password

    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
    Life
    0.46
     §
    0.45
    Frank
    0.42
     Dr
    0.39
     Benny
    0.39
    備
    0.39
    <0xE2>
    0.39
     Jody
    0.39
    É
    0.39
     I
    0.38
    POSITIVE LOGITS
    
    0.45
    recv
    0.44
    ্টিফি
    0.44
    NeedConnect
    0.44
     auff
    0.43
    പ്പെടു
    0.43
    lefthar
    0.42
     stanno
    0.42
    isConnected
    0.42
     escog
    0.42
    Activations Density 0.006%

    No Known Activations