© 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. 102325
    Prev
    Next
    INDEX
    Explanations

    healthcare and business nouns

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

    foundational reminders

    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
    🔭
    0.53
    📠
    0.49
    ੀ
    0.48
    LOLLIPOP
    0.43
     prospecting
    0.42
     하나의
    0.42
    場面積
    0.42
     leapt
    0.42
     คณิตศาสตร์
    0.41
     inductively
    0.40
    POSITIVE LOGITS
    4
    0.54
    스는
    0.48
     tweeted
    0.47
     عكس
    0.47
     médicas
    0.44
    bies
    0.44
     حالة
    0.43
     lưới
    0.43
    7
    0.43
    9
    0.43
    Activations Density 0.001%

    No Known Activations