© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117328
    Prev
    Next
    INDEX
    Explanations

    itch and scratch

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lipid
    -0.76
    וּ
    -0.73
     cavitation
    -0.73
     FACTORY
    -0.73
    chnen
    -0.73
    winder
    -0.71
    ricorn
    -0.71
     APPLICABLE
    -0.69
     eid
    -0.69
    zeppelin
    -0.69
    POSITIVE LOGITS
     itch
    3.17
     itching
    2.73
     itchy
    2.58
     scratching
    2.06
     scratch
    1.93
    Scratch
    1.91
     Scratch
    1.89
    scratch
    1.84
    itch
    1.62
     scratched
    1.59
    Activations Density 0.026%

    No Known Activations