© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 108993
    Prev
    Next
    INDEX
    Explanations

    terms, AD, CO, gang, magical

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     earners
    0.48
     Examiners
    0.45
    ्रे
    0.44
    이지만
    0.43
    िक
    0.42
    츄
    0.42
    mimeTypes
    0.41
     enabled
    0.41
     Genomics
    0.41
    ൺ
    0.41
    POSITIVE LOGITS
    教程
    0.53
     formación
    0.49
     нажа
    0.49
     não
    0.49
     conexión
    0.47
     formação
    0.46
     בין
    0.46
    ição
    0.46
     operação
    0.46
     Até
    0.46
    Activations Density 0.000%

    No Known Activations