© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 191839
    Prev
    Next
    INDEX
    Explanations

    XR and xargs -0

    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
     pressed
    0.45
     mid
    0.43
    dx
    0.40
    ο
    0.39
     skirt
    0.38
    昧
    0.38
     longer
    0.37
    mid
    0.37
     g
    0.36
     x
    0.36
    POSITIVE LOGITS
    𒋢
    0.42
    _{+}$
    0.42
    _{*}$
    0.41
     striées
    0.40
    reliant
    0.38
    BeanFactory
    0.38
     необы
    0.38
     ഇടപെ
    0.38
    isés
    0.37
    ằng
    0.37
    Activations Density 0.003%

    No Known Activations