© 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. 159666
    Prev
    Next
    INDEX
    Explanations

    you out

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

    kinetic energy

    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
    t
    0.57
     syphilis
    0.52
    that
    0.50
    have
    0.50
    v
    0.46
    시에
    0.46
    १
    0.45
    <0x80>
    0.44
     that
    0.44
    к
    0.44
    POSITIVE LOGITS
     pagal
    0.45
     واح
    0.45
     صوت
    0.44
     yaptı
    0.44
     خو
    0.43
     pār
    0.43
    গানি
    0.42
     gelato
    0.42
     Quadratic
    0.42
     سرد
    0.42
    Activations Density 0.000%

    No Known Activations