© 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. 197512
    Prev
    Next
    INDEX
    Explanations

    uses/functions

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

    use cases and applications

    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
     wreak
    0.57
     wre
    0.47
     ужа
    0.44
     Violation
    0.44
     transgression
    0.43
    헉
    0.41
     Вален
    0.41
     Occurrence
    0.41
     Joanne
    0.41
    👹
    0.40
    POSITIVE LOGITS
     χρήση
    0.51
    uses
    0.50
     utilizzo
    0.50
     использует
    0.48
     استفاده
    0.46
    izer
    0.46
     uses
    0.46
    Uses
    0.46
    inerja
    0.45
    ape
    0.45
    Activations Density 0.001%

    No Known Activations