© 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. 224893
    Prev
    Next
    INDEX
    Explanations

    mega, foil, delivered, unique, rating

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

    Metrics: SensorsAnalytics:

    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
    к
    0.49
     placés
    0.48
     catheters
    0.47
    Mâ
    0.47
     vacuoles
    0.47
    луб
    0.45
     кандида
    0.45
    ОР
    0.44
    ुत
    0.43
     elevados
    0.43
    POSITIVE LOGITS
    ,<
    0.54
     حرکت
    0.52
    :
    0.52
    ,【
    0.50
    ,|
    0.50
    কালীন
    0.49
     برنامه
    0.49
    ,»
    0.49
    layan
    0.48
    ,.
    0.47
    Activations Density 0.000%

    No Known Activations