© 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. 210924
    Prev
    Next
    INDEX
    Explanations

    delivery options available

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

    executed immediately

    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
    un
    0.48
    dai
    0.47
    n
    0.45
     součástí
    0.44
    的效果
    0.44
    st
    0.43
     man
    0.43
     sight
    0.43
     pozit
    0.43
     görünt
    0.42
    POSITIVE LOGITS
    жность
    0.52
     Beverage
    0.47
    稈
    0.47
     ৯ম
    0.47
    سكري
    0.46
    жному
    0.46
    боры
    0.46
     खेली
    0.45
    🍾
    0.45
    рс
    0.44
    Activations Density 0.000%

    No Known Activations