© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38877
    Prev
    Next
    INDEX
    Explanations

    acronyms and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ’
    -2.98
     garnered
    -2.59
    ”.
    -2.34
     There
    -2.30
     unrelenting
    -2.27
     touted
    -2.27
     Three
    -2.27
     Our
    -2.25
    忏
    -2.19
     According
    -2.16
    POSITIVE LOGITS
    t
    3.69
     quando
    2.88
     keď
    2.80
    derdag
    2.75
    ere
    2.75
    栳
    2.67
     vostre
    2.58
    wiliwch
    2.53
    est
    2.47
    l
    2.44
    Activations Density 0.033%

    No Known Activations