© 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. 179050
    Prev
    Next
    INDEX
    Explanations

    warranty or coding retreat

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

    English and Hindi words

    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
     краю
    0.50
    ịa
    0.49
     зву
    0.49
    기
    0.46
     इसका
    0.46
    íveis
    0.46
    вард
    0.46
    мую
    0.46
    embangunan
    0.46
     ನೋಡ
    0.45
    POSITIVE LOGITS
     subs
    0.49
    رز
    0.48
     Trained
    0.46
    0.44
     payments
    0.44
    payments
    0.44
     vlo
    0.44
     a
    0.44
    k
    0.44
     supports
    0.43
    Activations Density 0.000%

    No Known Activations