© 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. 145528
    Prev
    Next
    INDEX
    Explanations

    date and size indicators

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

    generating images or numbers

    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
    )^{[\
    0.54
    리와
    0.52
    팸
    0.52
    ᔾ
    0.50
    ትክል
    0.47
    얕
    0.47
    자들이
    0.47
    頬
    0.47
    არგ
    0.47
     symptômes
    0.44
    POSITIVE LOGITS
     عندك
    0.52
    aji
    0.51
     عليه
    0.51
    اي
    0.50
     verde
    0.48
     beste
    0.46
     motivo
    0.46
     فوق
    0.46
     или
    0.45
     prijs
    0.45
    Activations Density 0.001%

    No Known Activations