© 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. 21146
    Prev
    Next
    INDEX
    Explanations

    numbers and percentages

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

    mathematical calculations and equations

    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
    मारक
    0.58
    谲
    0.54
     вечер
    0.49
    Ü
    0.48
    цена
    0.48
     ресторан
    0.48
    કા
    0.46
     구매
    0.46
    구매
    0.46
     లేదా
    0.46
    POSITIVE LOGITS
    |
    0.42
    -
    0.41
     labile
    0.41
     ≈
    0.40
     perturbative
    0.40
     |=
    0.39
     thrombo
    0.39
     gravid
    0.39
     \
    0.39
     ||
    0.38
    Activations Density 0.000%

    No Known Activations