© 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. 84306
    Prev
    Next
    INDEX
    Explanations

    specific following terms

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

    Gemma, open weights

    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
    Ellipse
    0.51
    PR
    0.45
    らなかった
    0.43
    rigues
    0.42
    Defined
    0.42
    explained
    0.41
    Denominator
    0.41
    ('-
    0.41
    輕鬆
    0.41
    สวน
    0.41
    POSITIVE LOGITS
    ма
    0.52
    ме
    0.51
    тни
    0.50
    мета
    0.49
     occident
    0.49
     могут
    0.48
     அரசா
    0.48
     cât
    0.48
     periód
    0.47
     lớn
    0.47
    Activations Density 0.000%

    No Known Activations