© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 34694
    Prev
    Next
    INDEX
    Explanations

    javascript or typescript code

    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_40_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
     Sponsors
    0.39
    嫌
    0.38
    ផល
    0.37
     الحق
    0.37
     Reese
    0.36
    ผล
    0.36
    সঙ্ঘ
    0.35
    itschrift
    0.35
    RestorePolicy
    0.35
     açısından
    0.35
    POSITIVE LOGITS
    d
    0.43
    Bra
    0.42
    ደበ
    0.41
    دور
    0.39
     consistently
    0.38
    oor
    0.38
     Bra
    0.38
    tough
    0.38
    em
    0.37
    Coconut
    0.37
    Activations Density 0.000%

    No Known Activations