© 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. 219405
    Prev
    Next
    INDEX
    Explanations

    factual comparison

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

    definitions and explanations

    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
    堷
    0.50
     связь
    0.50
    补贴
    0.49
    пы
    0.49
    жы
    0.49
     нала
    0.49
     ખા
    0.47
     разде
    0.47
    поли
    0.46
    зы
    0.46
    POSITIVE LOGITS
    faktor
    0.49
    م
    0.46
    isn
    0.45
    för
    0.41
     listings
    0.40
     acrylonitrile
    0.40
    ysteem
    0.40
     facteur
    0.40
     eyepiece
    0.40
     측
    0.40
    Activations Density 0.000%

    No Known Activations