© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B-IT
    3. 13-GEMMASCOPE-2-RES-16K
    4. 3364
    Prev
    Next
    INDEX
    Explanations

    measurement units and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <unused2078>
    1.10
     zdjęcie
    1.09
    鐫
    1.08
     appunto
    1.08
    <unused609>
    1.08
     кожа
    1.08
    <unused790>
    1.07
    閭
    1.07
     rubrique
    1.07
     rufo
    1.07
    POSITIVE LOGITS
    -
    0.76
    Of
    0.73
    分散
    0.69
      
    0.68
    of
    0.66
    本
    0.62
     of
    0.57
     slow
    0.55
     na
    0.54
    antly
    0.53
    Activations Density 0.004%

    No Known Activations