© 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. 240876
    Prev
    Next
    INDEX
    Explanations

    time, places, and people

    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
     problematic
    0.45
     slit
    0.45
     thei
    0.42
     glycogen
    0.42
    맏
    0.42
     acetyl
    0.41
    يده
    0.41
     manslaughter
    0.41
    텐츠
    0.41
     hydride
    0.41
    POSITIVE LOGITS
    时间
    0.50
    的時間
    0.47
     کتاب
    0.47
     czasie
    0.47
    Від
    0.46
     pertinente
    0.46
    <h4>
    0.46
    Scientific
    0.45
    Minneapolis
    0.45
     چار
    0.44
    Activations Density 0.001%

    No Known Activations