© 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. 20503
    Prev
    Next
    INDEX
    Explanations

    Proper nouns and URLs

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

    social media and online business

    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
     VERY
    0.42
    ^{-(
    0.40
     -----------
    0.39
     --------
    0.39
     タイヤ
    0.39
    name
    0.39
    (&(
    0.39
     =========
    0.38
     መድ
    0.37
    ರುವುದು
    0.37
    POSITIVE LOGITS
     emigrated
    0.54
     Instagram
    0.52
     instagram
    0.50
     Daniela
    0.49
     유튜브
    0.49
    Instagram
    0.48
     Singapura
    0.47
     sympathique
    0.46
     ibn
    0.46
     Kız
    0.45
    Activations Density 0.001%

    No Known Activations