© 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. 157662
    Prev
    Next
    INDEX
    Explanations

    deal, shopping, price, offer

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

    concepts and examples

    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
    žka
    0.49
    die
    0.49
     下
    0.46
    ক্ষিতে
    0.46
    жко
    0.45
    bleshooting
    0.45
     बि
    0.44
    arcz
    0.44
    Blade
    0.44
     全
    0.43
    POSITIVE LOGITS
     frank
    0.50
     endot
    0.50
     rangi
    0.50
     menghubungi
    0.50
     autrefois
    0.50
     intranet
    0.49
     mit
    0.49
     assignment
    0.49
     et
    0.48
     nara
    0.48
    Activations Density 0.001%

    No Known Activations