© 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. 132335
    Prev
    Next
    INDEX
    Explanations

    partnership, then, Grit, guided

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

    inky face, same heat, rolling dice

    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
    de
    0.50
    the
    0.50
    :
    0.50
    ba
    0.48
    e
    0.48
    will
    0.48
    typical
    0.47
    }
    0.47
    og
    0.46
    othe
    0.46
    POSITIVE LOGITS
     palco
    0.55
     fato
    0.54
     dwind
    0.51
    始まる
    0.51
     roja
    0.48
     section
    0.48
     settore
    0.48
    岨
    0.47
     vamos
    0.47
     sól
    0.47
    Activations Density 0.003%

    No Known Activations