© 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. 237206
    Prev
    Next
    INDEX
    Explanations

    organ of the body

    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
     son
    0.55
     I
    0.52
    ?
    0.49
     is
    0.49
     upon
    0.49
     if
    0.49
    手的
    0.48
     Hand
    0.48
     Funcion
    0.48
     listens
    0.47
    POSITIVE LOGITS
    modification
    0.52
    thesis
    0.49
    nothing
    0.48
    matis
    0.48
    𝗱
    0.47
    gün
    0.46
     ተግባ
    0.46
    ارتی
    0.46
    deux
    0.46
    thread
    0.46
    Activations Density 0.000%

    No Known Activations