© 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. 190606
    Prev
    Next
    INDEX
    Explanations

    consult seller or service

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

    used for computing

    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
    \}.
    0.55
    লাষ
    0.51
     சிலை
    0.47
    ıkları
    0.47
     לח
    0.47
    rstrip
    0.47
    imageView
    0.46
     necessitated
    0.46
    י
    0.46
    ziert
    0.46
    POSITIVE LOGITS
    تباه
    0.52
     Gregory
    0.47
     Rogers
    0.46
     Driver
    0.46
     Cattle
    0.46
     Agriculture
    0.45
     Domestic
    0.45
     Emily
    0.43
     Analytic
    0.42
    কন
    0.42
    Activations Density 0.000%

    No Known Activations