© 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. 132729
    Prev
    Next
    INDEX
    Explanations

    past actions and states

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

    core concept

    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
     možda
    0.54
    ović
    0.53
    ńska
    0.49
     également
    0.47
     ở
    0.46
    ąp
    0.46
     обы
    0.46
     sắc
    0.46
     أيضا
    0.45
    可能会
    0.45
    POSITIVE LOGITS
    period
    0.44
     wides
    0.44
     सरकारने
    0.44
     Period
    0.43
     olds
    0.43
     Drinks
    0.43
    joined
    0.42
     तिथे
    0.41
    across
    0.41
    횡
    0.41
    Activations Density 0.003%

    No Known Activations