© 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. 20357
    Prev
    Next
    INDEX
    Explanations

    names, operations, requirements

    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
    合物
    0.50
    气体
    0.47
    开车
    0.47
    通勤
    0.46
    Jährige
    0.45
    笑顔
    0.44
    лее
    0.43
    な
    0.43
    करणा
    0.43
     направлении
    0.43
    POSITIVE LOGITS
     Croatia
    0.56
     countries
    0.50
     Serbia
    0.50
     markets
    0.48
     Bl
    0.48
     Europe
    0.48
     Chain
    0.48
     Agora
    0.47
     India
    0.47
     Paul
    0.46
    Activations Density 0.005%

    No Known Activations