© 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. 38526
    Prev
    Next
    INDEX
    Explanations

    actions involving time or resources

    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
    
    0.47
    質問
    0.47
     påver
    0.45
     질문
    0.45
     pronunci
    0.44
    昻
    0.44
    になっています
    0.44
     luxurious
    0.43
    舩
    0.42
    گه
    0.42
    POSITIVE LOGITS
    ro
    0.54
     Assistance
    0.51
    es
    0.49
    ie
    0.46
    k
    0.46
    in
    0.44
    rometry
    0.43
    u
    0.42
    er
    0.42
    ra
    0.42
    Activations Density 0.005%

    No Known Activations