© 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. 56827
    Prev
    Next
    INDEX
    Explanations

    integrals with `-ax`

    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
    e
    0.49
    ozy
    0.49
    i
    0.49
    information
    0.48
    hma
    0.47
    ons
    0.45
    polls
    0.45
    f
    0.45
    vá
    0.45
    in
    0.44
    POSITIVE LOGITS
     ಶಿವ
    0.50
    ਾਰੇ
    0.50
    ರ್ಥ
    0.49
    መር
    0.48
    قت
    0.48
    ગર
    0.47
    儋
    0.47
    
    0.47
    وت
    0.46
     spirited
    0.46
    Activations Density 0.002%

    No Known Activations