© 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. 189824
    Prev
    Next
    INDEX
    Explanations

    how did

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

    setting conditions or assumptions

    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
    k
    0.50
    c
    0.48
    ly
    0.48
    st
    0.48
    s
    0.48
     Ilya
    0.45
    termin
    0.44
    net
    0.42
    t
    0.42
    omorph
    0.42
    POSITIVE LOGITS
    CustomerID
    0.47
    在
    0.47
    拉克
    0.46
     Broughton
    0.46
    要在
    0.46
     доступа
    0.45
    在高
    0.45
    有力
    0.43
    豪華
    0.43
    可在
    0.42
    Activations Density 0.000%

    No Known Activations