© 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. 75322
    Prev
    Next
    INDEX
    Explanations

    post about, fret any, blend the

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

    specific concepts and components

    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
    颍
    0.48
    нями
    0.46
    <0xE3>
    0.46
    нев
    0.46
     яко
    0.45
    Ρ
    0.45
    (\\
    0.45
    天才
    0.44
     ста
    0.43
    خذ
    0.43
    POSITIVE LOGITS
     fostering
    0.52
     emphasizing
    0.51
     facilitating
    0.50
     kneading
    0.49
     acompañada
    0.49
     signifying
    0.49
     bezel
    0.48
     facilitation
    0.48
     reunion
    0.47
     configuring
    0.47
    Activations Density 0.001%

    No Known Activations