© 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. 89978
    Prev
    Next
    INDEX
    Explanations

    adjectives for nouns

    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
     преимуще
    0.51
     özelliği
    0.51
    蜗
    0.50
     każdy
    0.49
     όσο
    0.46
     거래
    0.46
     дослі
    0.46
     ờ
    0.46
     მათი
    0.46
    lockSeconds
    0.45
    POSITIVE LOGITS
    ಣ
    0.54
    ли
    0.54
     push
    0.49
    ar
    0.48
     cadmium
    0.46
    ing
    0.46
     permit
    0.46
    ड़क
    0.46
     rad
    0.45
    рь
    0.45
    Activations Density 0.000%

    No Known Activations