© 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. 62936
    Prev
    Next
    INDEX
    Explanations

    abbreviations common in lists and data

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

    imread.py.jscv2filevariable

    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
    1.37
    an
    1.25
    is
    1.23
    er
    1.13
    at
    1.13
    ა
    1.04
    en
    1.02
    el
    0.99
    have
    0.99
    has
    0.99
    POSITIVE LOGITS
    و
    0.86
    ו
    0.86
    ك
    0.83
     пси
    0.75
     quake
    0.70
     mezzanine
    0.67
     techs
    0.66
     ιδια
    0.66
     незна
    0.63
     جسم
    0.63
    Activations Density 0.035%

    No Known Activations