© 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. 100555
    Prev
    Next
    INDEX
    Explanations

    present-day locations

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

    modern-day locations

    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
     Raster
    0.42
     (**
    0.42
     akhir
    0.41
     Tony
    0.41
     Flux
    0.41
     இறுதி
    0.40
     Enabled
    0.40
     இதுவரை
    0.39
    **:
    0.39
     anf
    0.38
    POSITIVE LOGITS
     devenu
    0.54
     devenue
    0.52
     renamed
    0.49
    落
    0.48
     落
    0.46
     букме
    0.45
    Msg
    0.44
    现在的
    0.44
     geworden
    0.44
    adays
    0.43
    Activations Density 0.080%

    No Known Activations