© 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. 116888
    Prev
    Next
    INDEX
    Explanations

    CDs and physical media

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

    APIs, ID, convolutions, Transforms

    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
    oi
    0.56
    ,:
    0.53
    linha
    0.52
     Francesca
    0.49
    oe
    0.48
     fisher
    0.48
    uri
    0.47
     Hitler
    0.47
    ani
    0.46
    ah
    0.46
    POSITIVE LOGITS
    म्भ
    0.52
    तालों
    0.49
    숑
    0.46
    த்தொ
    0.44
    ্যোগ
    0.44
    ড়যন্ত্র
    0.43
    кой
    0.43
    ➹
    0.43
    व्यों
    0.43
    रेज
    0.42
    Activations Density 0.000%

    No Known Activations