© 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. 161699
    Prev
    Next
    INDEX
    Explanations

    divisional performance

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

    Avoid phone, Elon Musk

    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
    居民
    0.44
    irani
    0.44
     meagre
    0.44
    、
    0.43
    ందని
    0.43
    （
    0.42
    eteers
    0.42
     मुद्राओं
    0.42
     roadways
    0.41
     flimsy
    0.40
    POSITIVE LOGITS
     počet
    0.52
     सार
    0.48
     God
    0.46
     отвер
    0.46
     Gott
    0.44
    诀
    0.44
     ভাগ
    0.43
     jedno
    0.43
     ich
    0.43
     Perl
    0.42
    Activations Density 0.001%

    No Known Activations