© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 33665
    Prev
    Next
    INDEX
    Explanations

    Photos and visual concepts

    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_40_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
     captcha
    0.39
     procedure
    0.38
     sieht
    0.38
     chiens
    0.38
     """)
    0.38
     ಸ್ವಲ್ಪ
    0.38
    ","#
    0.37
    ("#
    0.37
     simplification
    0.37
    غام
    0.37
    POSITIVE LOGITS
    Photos
    0.53
     Photos
    0.49
    photos
    0.47
     photos
    0.43
     плане
    0.43
    Khan
    0.43
    aj
    0.42
    agor
    0.42
     fotos
    0.41
     фотографии
    0.41
    Activations Density 0.000%

    No Known Activations