© 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. 133991
    Prev
    Next
    INDEX
    Explanations

    Canada government, comparisons, specific foods, core skills, high power

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

    than some

    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
    ə
    0.53
    裒
    0.52
    laublich
    0.51
    ע
    0.50
     своє
    0.48
     успі
    0.48
    መሳሳይ
    0.47
    д
    0.47
    م
    0.46
    ᷄
    0.46
    POSITIVE LOGITS
    cardNumber
    0.45
    centos
    0.45
     cei
    0.42
    ñada
    0.42
     vida
    0.41
     موجود
    0.41
     surreal
    0.41
    ../../../
    0.41
    ğı
    0.41
     quickly
    0.40
    Activations Density 0.000%

    No Known Activations