© 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. 249592
    Prev
    Next
    INDEX
    Explanations

    used as function/purpose

    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
     endlessly
    0.43
    ీల
    0.42
     двадцать
    0.41
     sorely
    0.40
    étrique
    0.39
    compassing
    0.38
    晌
    0.38
    teres
    0.38
     contrario
    0.38
     hogi
    0.38
    POSITIVE LOGITS
    :
    0.52
    :+
    0.48
    ：
    0.48
     ferns
    0.47
    :</
    0.45
     OTHER
    0.42
    ņas
    0.41
     Gators
    0.41
     অন্যান্য
    0.41
    服装
    0.41
    Activations Density 0.000%

    No Known Activations