© 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. 45992
    Prev
    Next
    INDEX
    Explanations

    . followed by numbers

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

    money figures and math

    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
     shortcomings
    0.51
     probed
    0.50
     perceptive
    0.48
     asymmetries
    0.47
     Š
    0.47
     inhomogeneities
    0.47
     apl
    0.47
     Bessel
    0.46
     shadowing
    0.45
     anteced
    0.44
    POSITIVE LOGITS
    طانیہ
    0.46
    utenção
    0.46
    Reducer
    0.46
    Illegal
    0.44
    ómago
    0.42
    owią
    0.42
    出门
    0.42
    发动机
    0.41
    सुबह
    0.40
    汽
    0.40
    Activations Density 0.000%

    No Known Activations