© 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. 21461
    Prev
    Next
    INDEX
    Explanations

    URLs and links

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

    urls

    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
     studenti
    0.41
     amante
    0.41
     dever
    0.40
    melidir
    0.39
     ister
    0.37
     werden
    0.37
    ரண
    0.37
    䅡
    0.37
     entro
    0.37
     arbete
    0.37
    POSITIVE LOGITS
     вроде
    0.52
    https
    0.46
    比如
    0.46
     Apparently
    0.46
    论坛
    0.45
    Apparently
    0.44
    ttps
    0.44
    যদিও
    0.43
     اهو
    0.43
    好像
    0.43
    Activations Density 0.018%

    No Known Activations