© 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. 243550
    Prev
    Next
    INDEX
    Explanations

    in young keep the

    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
     fluctuations
    0.52
    س
    0.47
    inct
    0.46
    الی
    0.46
    are
    0.45
     oscill
    0.45
     জিনি
    0.44
    ش
    0.44
     fluctuation
    0.43
    OrderID
    0.42
    POSITIVE LOGITS
     hlavní
    0.50
     blieb
    0.50
     zunächst
    0.49
    ɠ
    0.48
     నేపథ
    0.48
     responsável
    0.48
     maß
    0.47
     adequado
    0.47
     Verantwortung
    0.47
    猀
    0.47
    Activations Density 0.001%

    No Known Activations