© 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. 125762
    Prev
    Next
    INDEX
    Explanations

    dust & allergens

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

    .append() method

    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
    şe
    0.52
    s
    0.51
    uti
    0.47
    推荐
    0.47
    ısıyla
    0.46
    če
    0.46
     Министер
    0.46
    şi
    0.45
    pov
    0.44
     करा
    0.44
    POSITIVE LOGITS
    скохозяй
    0.50
     innego
    0.50
    餓
    0.49
    覬
    0.46
    ิล
    0.46
     ／
    0.46
     humain
    0.45
     atof
    0.44
     logarith
    0.44
    ಬ
    0.44
    Activations Density 0.000%

    No Known Activations