© 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. 40-GEMMASCOPE-2-RES-262K
    7. 2607
    Prev
    Next
    INDEX
    Explanations

    maximum and minimum

    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
    打电话
    0.41
    忏
    0.41
    䔋
    0.40
    contentType
    0.40
    oldCount
    0.38
     tato
    0.38
     इंद्र
    0.38
     созна
    0.38
    㝒
    0.38
    鸿
    0.38
    POSITIVE LOGITS
     highest
    1.13
     max
    1.09
    max
    1.06
     largest
    1.05
     maxima
    1.03
    Highest
    1.03
    Largest
    1.02
     Highest
    1.02
     maximum
    1.01
    highest
    1.00
    Activations Density 0.033%

    No Known Activations