© 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-65K
    7. 49621
    Prev
    Next
    INDEX
    Explanations

    window capture, Booking, sensors, glass, power

    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_65k_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
    isia
    0.40
    enger
    0.40
    side
    0.39
    ј
    0.39
     lemon
    0.39
    側
    0.38
    ibre
    0.38
     Lemon
    0.38
    ulele
    0.38
    unicode
    0.37
    POSITIVE LOGITS
    GOING
    0.40
    पीएम
    0.38
    दात
    0.38
     đâu
    0.38
    Regulations
    0.38
    SourceRequest
    0.37
     regler
    0.36
     탁
    0.36
     Mois
    0.36
    ྀ
    0.36
    Activations Density 0.001%

    No Known Activations