© 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. 62657
    Prev
    Next
    INDEX
    Explanations

    85 percent/billion/jobs/buyers

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

    85, 1385, 8517, 856

    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
     רי
    0.43
     inox
    0.42
     '';
    0.41
     منه
    0.40
    ไลน์
    0.39
    ूथ
    0.39
     kategorie
    0.39
     linee
    0.38
    ꒱
    0.38
     inoxidable
    0.38
    POSITIVE LOGITS
     megs
    0.48
    orns
    0.47
    逼
    0.45
    gang
    0.44
    ack
    0.43
    ueling
    0.42
    embark
    0.42
    ensi
    0.41
    cz
    0.40
    abytes
    0.39
    Activations Density 0.008%

    No Known Activations