© 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. 111323
    Prev
    Next
    INDEX
    Explanations

    button, slot, or %

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

    related to power, support, or differences

    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
     endeavour
    0.44
     उल्
    0.43
     дося
    0.43
     Embr
    0.42
     Antes
    0.40
     pursuits
    0.40
     Installer
    0.39
    ;
    0.39
     آف
    0.39
    Alias
    0.39
    POSITIVE LOGITS
    特集
    0.51
     másik
    0.48
    座位
    0.46
    ᴀ
    0.44
    ftest
    0.44
    to
    0.44
     urinary
    0.43
    வேறு
    0.42
    站点
    0.42
    മായും
    0.42
    Activations Density 0.004%

    No Known Activations