© 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. 228970
    Prev
    Next
    INDEX
    Explanations

    field below

    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
     бо
    0.52
    vět
    0.52
    vai
    0.50
     аэро
    0.49
     Megh
    0.48
     గా
    0.48
    ти
    0.47
    돠
    0.47
    aitan
    0.46
    キラ
    0.46
    POSITIVE LOGITS
     molte
    0.45
     স্বাক্ষ
    0.45
     diagnostics
    0.45
     fnt
    0.45
     respectively
    0.44
     genes
    0.44
     trimethyl
    0.44
     embeddings
    0.43
    পন্থী
    0.43
     Antibody
    0.43
    Activations Density 0.002%

    No Known Activations