© 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. 55915
    Prev
    Next
    INDEX
    Explanations

    describing qualities of nouns

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

    Canadian surface

    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
     appli
    0.49
     навча
    0.48
     fluent
    0.47
    ﺭ
    0.46
     regexp
    0.43
    Vecchio
    0.43
     Fluent
    0.43
     Cochrane
    0.43
    मारी
    0.42
    ജന
    0.42
    POSITIVE LOGITS
    hubung
    0.49
    %%
    0.46
    ón
    0.46
    ِينَ
    0.46
    adı
    0.45
    뤘
    0.43
    >%
    0.43
    yal
    0.43
    टकों
    0.43
    ɕ
    0.43
    Activations Density 0.000%

    No Known Activations