© 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. 190024
    Prev
    Next
    INDEX
    Explanations

    describing outcomes, conditions, or qualities

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

    skill development and classifications

    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
    ibold
    0.54
     технологии
    0.47
    ystone
    0.46
    indruck
    0.46
     enlaces
    0.46
    ix
    0.43
     পাকসেন
    0.43
    ≤
    0.43
    ín
    0.42
     reprises
    0.42
    POSITIVE LOGITS
    ാർ
    0.50
    衛生
    0.46
    InCM
    0.46
    Health
    0.45
    ToAction
    0.44
    Mz
    0.44
    ტო
    0.43
    Kamu
    0.43
    Capacity
    0.43
    Chemistry
    0.43
    Activations Density 0.001%

    No Known Activations