© 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. 181464
    Prev
    Next
    INDEX
    Explanations

    actions or experiences

    np_acts-logits-general · gemini-2.5-flash-lite

    I/We describing past experiences

    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
    sou
    0.54
    arl
    0.50
    Er
    0.49
    rem
    0.48
    a
    0.48
    our
    0.48
    dirt
    0.47
     ricord
    0.47
    hal
    0.47
     ghi
    0.47
    POSITIVE LOGITS
    려고
    0.46
     DOI
    0.42
     verwendeten
    0.42
     디자인
    0.40
     사용하는
    0.40
     인터넷
    0.39
     linearized
    0.39
     मैट्र
    0.39
    市
    0.38
    widgetTo
    0.38
    Activations Density 0.002%

    No Known Activations