© 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. 29673
    Prev
    Next
    INDEX
    Explanations

    great publishing

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

    appearance and sensory details

    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
    {\'
    0.47
     worldwide
    0.47
     Worldwide
    0.44
     de
    0.42
    //$
    0.41
    Worldwide
    0.41
    ofa
    0.41
    🏁
    0.41
    worldwide
    0.41
    同じ
    0.40
    POSITIVE LOGITS
     식품
    0.47
     반지름
    0.46
     మొక్క
    0.44
    icuously
    0.43
    ränkt
    0.41
     뭔
    0.41
     lasso
    0.41
    이지만
    0.41
     lurking
    0.40
     带
    0.40
    Activations Density 0.000%

    No Known Activations