© 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. 1845
    Prev
    Next
    INDEX
    Explanations

    Mc-Arthur, David-Ross names

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

    javascript imports and configurations

    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
    ها
    0.55
    jelder
    0.54
    ؛
    0.53
    ября
    0.52
    或
    0.52
    seits
    0.51
    quefois
    0.51
    కు
    0.51
    URNIZOR
    0.51
    necked
    0.51
    POSITIVE LOGITS
     useDispatch
    0.66
     descendants
    0.59
     useState
    0.58
     BrowserRouter
    0.56
     resett
    0.53
     goTo
    0.52
     create
    0.52
     customers
    0.50
     factorial
    0.50
     C
    0.49
    Activations Density 0.000%

    No Known Activations