© 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. 45914
    Prev
    Next
    INDEX
    Explanations

    adjust your settings

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

    technical and functional terms

    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
     I
    0.61
     &
    0.55
    i
    0.50
     The
    0.49
     L
    0.49
     V
    0.47
     All
    0.47
     C
    0.46
     J
    0.46
     Piazza
    0.46
    POSITIVE LOGITS
     atributo
    0.57
     folosit
    0.54
     параметра
    0.53
    atributo
    0.52
     profesora
    0.52
     atthakath
    0.52
     Gebrauch
    0.50
    ровой
    0.50
     podataka
    0.50
     naszego
    0.49
    Activations Density 0.000%

    No Known Activations