© 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. 133997
    Prev
    Next
    INDEX
    Explanations

    be purchased

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

    variar, vary, varies

    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
     говорится
    0.47
    佃
    0.47
    2
    0.47
    ATE
    0.45
     আদৌ
    0.45
    UNCH
    0.45
     deprive
    0.44
    APPY
    0.44
    倫
    0.43
    ADDING
    0.43
    POSITIVE LOGITS
    TimeSeries
    0.59
    voir
    0.49
     tritt
    0.47
     ķ
    0.47
    tic
    0.47
     procl
    0.47
    куль
    0.46
     ist
    0.45
    tics
    0.45
    ksz
    0.44
    Activations Density 0.001%

    No Known Activations