© 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. 149437
    Prev
    Next
    INDEX
    Explanations

    financial, technical, or descriptive phrases

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

    lists and reminders

    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
    ्रिया
    0.45
    dincer
    0.43
    toluene
    0.43
    sdl
    0.43
    則
    0.42
    ಇದ
    0.42
    Ꮠ
    0.42
    ኻ
    0.41
     シャ
    0.40
    வனே
    0.40
    POSITIVE LOGITS
     Ivory
    0.47
     NDVI
    0.46
     күзгү
    0.45
    vest
    0.45
    voi
    0.45
    ênd
    0.43
     estimates
    0.43
     overlapped
    0.43
     overloaded
    0.42
     iPad
    0.42
    Activations Density 0.002%

    No Known Activations