© 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. 41847
    Prev
    Next
    INDEX
    Explanations

    services delivering

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

    region, calculating, ingredients, registration

    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
    ’
    0.47
    ception
    0.46
    hybrid
    0.46
    ৃত্তি
    0.46
    !
    0.45
     distinctly
    0.45
    start
    0.44
     stared
    0.43
     Europeans
    0.43
    שוט
    0.43
    POSITIVE LOGITS
     menuMobile
    0.48
     регистра
    0.46
    зак
    0.46
     достав
    0.45
    伤害
    0.45
    調
    0.44
     खर्च
    0.43
     delivering
    0.43
     напол
    0.42
     marginRight
    0.42
    Activations Density 0.000%

    No Known Activations