© 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. 209692
    Prev
    Next
    INDEX
    Explanations

    automotive, workshops, or individually

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

    based on categories

    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
     overcoming
    0.46
     outil
    0.46
     banyaknya
    0.45
     Dri
    0.44
    리
    0.44
     computadora
    0.44
     অপারেটিং
    0.44
     améliorer
    0.44
     overcame
    0.44
     exoskeleton
    0.44
    POSITIVE LOGITS
    傳
    0.49
    insk
    0.44
    ія
    0.44
    传
    0.43
    oppers
    0.43
     Лей
    0.42
    ifest
    0.41
    jekt
    0.41
    ِح
    0.41
    ERO
    0.41
    Activations Density 0.001%

    No Known Activations