© 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-65K
    7. 49266
    Prev
    Next
    INDEX
    Explanations

    names and their associated descriptors

    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
    姓
    0.41
     housework
    0.40
     oneself
    0.40
     thoe
    0.39
    "
    0.39
     Peking
    0.37
    qrcode
    0.37
    QRCode
    0.37
     ":
    0.37
     Hunan
    0.37
    POSITIVE LOGITS
    ack
    0.45
    Tech
    0.43
    റ്റർ
    0.42
     Royale
    0.41
    Shows
    0.41
    ﻑ
    0.41
    renaline
    0.39
    ائي
    0.39
     retomar
    0.39
    য়নের
    0.39
    Activations Density 0.004%

    No Known Activations