© 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. 134988
    Prev
    Next
    INDEX
    Explanations

    Company, prompt, results, Media, medical

    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
    椏
    0.49
     دوبارہ
    0.49
     খারাপ
    0.45
     както
    0.44
     ત્રણ
    0.43
     پکڑ
    0.43
     потому
    0.42
     ઘણી
    0.41
     сім
    0.41
     છીએ
    0.40
    POSITIVE LOGITS
    oyeva
    0.50
    pc
    0.48
    tsp
    0.47
    lte
    0.47
    wig
    0.46
    疏
    0.45
     dzień
    0.45
    の名
    0.44
    lsp
    0.44
    dea
    0.44
    Activations Density 0.000%

    No Known Activations