© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 84000
    Prev
    Next
    INDEX
    Explanations

    largest, big, fat

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

    sexual excitement

    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
    ীন্দ্র
    0.54
     δημο
    0.51
     اظہار
    0.51
    <unused37>
    0.49
    νος
    0.48
    WriteString
    0.46
    ιος
    0.46
    Circuit
    0.46
    ività
    0.46
     ద్వారా
    0.46
    POSITIVE LOGITS
    k
    0.65
    b
    0.52
    w
    0.52
    y
    0.52
    ft
    0.52
    o
    0.50
    g
    0.50
    !!)
    0.49
    //
    0.49
    !).
    0.49
    Activations Density 0.000%

    No Known Activations