© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 187670
    Prev
    Next
    INDEX
    Explanations

    onboard experiences

    np_acts-logits-general · gemini-2.5-flash-lite

    import json, page, travel, chain, focuses, individual

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    centro
    0.48
     করণ
    0.47
     ماين
    0.45
    elmi
    0.45
    URANCE
    0.45
    ㎖
    0.44
    childComplexity
    0.44
     فلسط
    0.43
    trecht
    0.43
     څرنګ
    0.43
    POSITIVE LOGITS
     accepting
    0.50
    ᡳ
    0.49
     approving
    0.49
     escapar
    0.49
     произведение
    0.48
     принима
    0.48
     accepts
    0.47
    یر
    0.46
    騷
    0.46
     cigars
    0.44
    Activations Density 0.000%

    No Known Activations