© 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. 73224
    Prev
    Next
    INDEX
    Explanations

    created in, chilly days

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

    introduces topics or actions

    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
    Р
    0.57
    標
    0.55
    Moon
    0.47
    )+\
    0.46
    勧め
    0.46
    信頼
    0.45
     سپورت
    0.45
    П
    0.45
    Л
    0.45
     تاسو
    0.43
    POSITIVE LOGITS
    veh
    0.64
     vehicular
    0.59
    anians
    0.52
    änk
    0.52
    aneous
    0.51
    aurants
    0.51
     Concrete
    0.50
    oders
    0.50
    cken
    0.50
    gomery
    0.49
    Activations Density 0.001%

    No Known Activations