© 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. 12062
    Prev
    Next
    INDEX
    Explanations

    chess notation or programming

    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
    谈
    0.47
     цих
    0.44
     бизнеса
    0.43
     этих
    0.43
    地位
    0.42
    ኛውም
    0.42
    竞
    0.42
    一样
    0.41
    讨论
    0.41
    客观
    0.41
    POSITIVE LOGITS
     domains
    0.51
     genomes
    0.49
     intraper
    0.47
     rápida
    0.47
     fille
    0.47
     curves
    0.46
     macroph
    0.46
     bullets
    0.45
     slabs
    0.45
     symplectic
    0.45
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.