© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 20638
    Prev
    Next
    INDEX
    Explanations

    cardiology, et al

    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
    감
    0.43
     пря
    0.42
    Shin
    0.42
    వ
    0.41
    sign
    0.40
    版本
    0.39
    دل
    0.39
     ત
    0.39
    tipo
    0.39
     бекер
    0.39
    POSITIVE LOGITS
    ایی
    0.56
    amburger
    0.51
     Bamberg
    0.50
     पोहो
    0.50
     Cardiology
    0.50
     Danube
    0.49
     PCP
    0.49
     juggling
    0.48
     politely
    0.47
    ppelin
    0.46
    Activations Density 0.000%

    No Known Activations