© 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. 134005
    Prev
    Next
    INDEX
    Explanations

    simpler as crash

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

    invert before root

    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
     衣
    0.47
    Ẫ
    0.45
    <0x80>
    0.43
    aacute
    0.43
     কম
    0.42
    isha
    0.42
    pmap
    0.41
    ทราบ
    0.41
     acquainted
    0.40
    ｚ
    0.40
    POSITIVE LOGITS
    Type
    0.44
     науки
    0.42
     recouvre
    0.42
    Unfortunately
    0.41
     Chew
    0.41
    นู
    0.41
     помимо
    0.40
    Minor
    0.40
    พัน
    0.40
    Wald
    0.40
    Activations Density 0.002%

    No Known Activations