© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 251586
    Prev
    Next
    INDEX
    Explanations

    skin conditions and wounds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Pitch
    0.66
    tag
    0.53
    Implementation
    0.50
    Psych
    0.49
    Altitude
    0.49
    pitch
    0.48
    this
    0.47
    ?
    0.47
    subset
    0.47
    eus
    0.47
    POSITIVE LOGITS
     relieves
    0.50
     callus
    0.50
     pute
    0.48
     moistened
    0.48
     exud
    0.46
     suscit
    0.45
     luoghi
    0.45
     neka
    0.45
     inflict
    0.44
     dampened
    0.44
    Activations Density 0.001%

    No Known Activations