© 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. 33226
    Prev
    Next
    INDEX
    Explanations

    multiplication followed by parenthesis

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

    mathematical and financial formulas

    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
     Your
    0.48
    缡
    0.46
     $$$
    0.45
     your
    0.43
    你的
    0.43
    ifel
    0.43
    ឹង
    0.42
     ඔබේ
    0.42
     YOUR
    0.42
     вашей
    0.42
    POSITIVE LOGITS
    ^{(
    0.48
     underwent
    0.42
     გავ
    0.41
    ٴ
    0.40
    初の
    0.40
     horribly
    0.40
     suffis
    0.39
     maîtrise
    0.39
    discovery
    0.38
    usetts
    0.38
    Activations Density 0.000%

    No Known Activations