© 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. 32314
    Prev
    Next
    INDEX
    Explanations

    already set, save more

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

    armed, maintain, networks, learn

    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
    精致
    0.50
    挨
    0.46
     synov
    0.46
    𝐽
    0.45
    合计
    0.45
     gurus
    0.45
    并不
    0.44
    细胞
    0.44
     sushi
    0.44
     理解
    0.43
    POSITIVE LOGITS
    ერ
    0.56
    the
    0.48
    3
    0.47
    umm
    0.46
    arsk
    0.46
    auch
    0.44
    that
    0.44
    autom
    0.44
     tena
    0.43
    EXTERNAL
    0.43
    Activations Density 0.000%

    No Known Activations