© 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. 2506
    Prev
    Next
    INDEX
    Explanations

    writing and drawing marks

    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
     leveraged
    0.39
    FAQ
    0.38
    btnUn
    0.38
     DDoS
    0.37
     Kubernetes
    0.36
    packaged
    0.36
    %{
    0.36
     powertrain
    0.35
    ⮕
    0.35
     metaverse
    0.35
    POSITIVE LOGITS
     scribble
    1.75
     scrib
    1.69
     pencil
    1.58
     handwriting
    1.56
     doodles
    1.44
     Pencil
    1.40
    pencil
    1.34
     पेंसिल
    1.34
     pen
    1.32
     scribe
    1.32
    Activations Density 0.059%

    No Known Activations