© 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. 223153
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts

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

    process or calculation comparison

    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
     која
    0.50
    τύ
    0.45
     retrieve
    0.43
     Π
    0.43
    此
    0.43
     (
    0.42
     species
    0.42
    Download
    0.42
    Saxon
    0.41
     Время
    0.41
    POSITIVE LOGITS
    '];?>
    0.43
     основной
    0.42
    primary
    0.42
    endedores
    0.41
     lichaam
    0.41
    getCql
    0.41
     consulter
    0.40
     مدير
    0.40
     আঙ্গ
    0.40
    স্তাফ
    0.40
    Activations Density 0.002%

    No Known Activations