© 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. 184279
    Prev
    Next
    INDEX
    Explanations

    from text segments

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

    verbosity level, chapter following, demos, regex §

    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
     a
    0.60
     the
    0.51
    periodic
    0.48
     their
    0.47
    b
    0.46
    ᴀ
    0.45
    a
    0.44
     Chatham
    0.43
    ୯
    0.43
    bong
    0.42
    POSITIVE LOGITS
     desenho
    0.55
     fawn
    0.51
     kilka
    0.50
    ക്കാല
    0.48
     prawie
    0.48
     Кали
    0.48
     Фургала
    0.48
     війни
    0.48
     encapsulate
    0.48
    رت
    0.47
    Activations Density 0.000%

    No Known Activations