© 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. 200430
    Prev
    Next
    INDEX
    Explanations

    conditional or final stages

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

    creative writing and medical information

    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
    ..
    0.46
    =>
    0.46
     아닙
    0.46
    customerId
    0.46
    Cod
    0.45
    TARGET
    0.45
    —
    0.45
    --
    0.45
    utton
    0.44
    POSITIVE LOGITS
     verbinden
    0.49
    grains
    0.47
     প্রবন্ধে
    0.46
     ouv
    0.44
     przyj
    0.44
     Vieni
    0.43
     retelling
    0.43
    াজিক
    0.42
     fluido
    0.42
    礪
    0.41
    Activations Density 0.002%

    No Known Activations