© 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. 9009
    Prev
    Next
    INDEX
    Explanations

    technical configuration and web settings

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

    code and file paths

    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
    뮐
    0.28
     aHUS
    0.28
     хірур
    0.28
    thisTrack
    0.27
    SRPI
    0.25
    摻
    0.25
    TARGETTING
    0.25
    鳃
    0.25
    URNIZOR
    0.25
     cannula
    0.24
    POSITIVE LOGITS
    /
    0.33
    -
    0.30
    Config
    0.28
     web
    0.26
    web
    0.26
     GUI
    0.26
     Core
    0.26
     Web
    0.26
    d
    0.25
     Settings
    0.25
    Activations Density 0.018%

    No Known Activations