© 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. 80663
    Prev
    Next
    INDEX
    Explanations

    quick safety

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

    logic gates and sequences

    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
     첫
    0.49
     उसे
    0.49
    これを
    0.48
    ہرست
    0.46
    تحان
    0.46
    ེ་
    0.45
     carcinogenesis
    0.44
    ել
    0.44
     ބ
    0.44
     시즌
    0.44
    POSITIVE LOGITS
    ching
    0.49
    llan
    0.47
    alk
    0.44
    ferenz
    0.44
    涑
    0.43
    龄
    0.43
    cha
    0.42
    etur
    0.41
    riva
    0.41
    ché
    0.40
    Activations Density 0.000%

    No Known Activations