© 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. 2740
    Prev
    Next
    INDEX
    Explanations

    original before nouns/adjectives

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

    original

    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
     dibujar
    0.59
    িং
    0.58
     prelim
    0.57
     previo
    0.56
    充実
    0.52
     pouvez
    0.52
     düz
    0.52
    δ
    0.52
     sensibilidad
    0.51
     risultato
    0.50
    POSITIVE LOGITS
    original
    1.69
     original
    1.57
     Original
    1.48
     originale
    1.48
     ORIGINAL
    1.45
    Original
    1.41
     ориги
    1.34
     оригі
    1.31
     originals
    1.29
     orijinal
    1.29
    Activations Density 0.060%

    No Known Activations