© 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. 12603
    Prev
    Next
    INDEX
    Explanations

    finding information and popular topics

    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
     delineation
    0.46
     granulation
    0.46
    েন্দ্র
    0.41
     description
    0.39
    ಾಯ
    0.39
    
    0.39
     culprit
    0.38
    :'],
    0.38
     vignettes
    0.38
    𒆳
    0.38
    POSITIVE LOGITS
     Discover
    0.52
    FAQ
    0.50
     Find
    0.50
    find
    0.49
     Popular
    0.48
     Privacy
    0.48
    Popular
    0.48
    Upload
    0.47
    privacy
    0.47
    Privacy
    0.46
    Activations Density 0.000%

    No Known Activations