© 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. 193366
    Prev
    Next
    INDEX
    Explanations

    substitution

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

    translations and probability

    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
    다
    0.48
     ತನ್ನ
    0.46
    nights
    0.45
    тем
    0.44
    ตน
    0.44
    證
    0.43
    บัน
    0.42
    ‟
    0.41
    пол
    0.40
    гра
    0.39
    POSITIVE LOGITS
     ciencia
    0.50
     Bolsonaro
    0.48
     recomendaciones
    0.48
    getImageFolder
    0.48
     Insect
    0.48
     insect
    0.48
     biodivers
    0.47
     brillantes
    0.47
     cenas
    0.47
     политики
    0.47
    Activations Density 0.000%

    No Known Activations