© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 123972
    Prev
    Next
    INDEX
    Explanations

    evaluates and evaluations

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

    areas discussing sales

    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
     छो
    0.61
    的時候
    0.57
    十
    0.55
     детей
    0.48
    Ли
    0.48
     шко
    0.47
    Classe
    0.47
     posso
    0.47
    я
    0.47
     ছেড়ে
    0.47
    POSITIVE LOGITS
     disruptions
    0.47
     inroads
    0.45
     evaluations
    0.42
     inhibit
    0.42
    වේ
    0.41
     impediments
    0.41
    ුවේ
    0.41
     evaluaciones
    0.41
     evaluates
    0.40
     opponents
    0.38
    Activations Density 0.000%

    No Known Activations