© 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. 135167
    Prev
    Next
    INDEX
    Explanations

    6.1-inch LCD

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

    Ability, Possibility, Current, Plots

    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
     JET
    0.51
    Nú
    0.50
     seduced
    0.50
     disulfide
    0.49
     १३
    0.49
     छ
    0.48
     ५
    0.48
    JET
    0.48
     صہیونی
    0.47
     இதற்கு
    0.47
    POSITIVE LOGITS
    ↵↵
    0.47
    nd
    0.44
    ="
    0.43
    Andrews
    0.43
     Compos
    0.43
     だけ
    0.42
    arelli
    0.42
    ustum
    0.42
    ib
    0.42
    emek
    0.42
    Activations Density 0.000%

    No Known Activations