© 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. 243276
    Prev
    Next
    INDEX
    Explanations

    infant

    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
    제
    0.57
    este
    0.47
    ிற
    0.46
    advert
    0.46
    ри
    0.45
    uomo
    0.45
    재
    0.45
    ре
    0.45
    Image
    0.44
    کر
    0.44
    POSITIVE LOGITS
     DOE
    0.52
     Cancun
    0.47
     CTE
    0.47
     Син
    0.46
     Mik
    0.46
    obos
    0.46
     Newer
    0.44
     depositphotos
    0.44
     {}>,
    0.44
     GaAs
    0.44
    Activations Density 0.001%

    No Known Activations