© 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. 74807
    Prev
    Next
    INDEX
    Explanations

    adhesive vinyl labels

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

    product names and descriptions

    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
    🤨
    0.46
     kabhi
    0.44
    そもそも
    0.42
    https
    0.42
    จุบัน
    0.42
    कांग्रेस
    0.42
    Indeed
    0.41
    देन
    0.41
     Kabhi
    0.40
     provinsi
    0.39
    POSITIVE LOGITS
     perforated
    0.45
    镙
    0.45
     Beech
    0.44
     Floral
    0.44
    raper
    0.43
     jär
    0.42
     Toy
    0.41
     Thermal
    0.41
     வெளிப்புற
    0.41
    较
    0.41
    Activations Density 0.008%

    No Known Activations