© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 9785
    Prev
    Next
    INDEX
    Explanations

    computing hardware and software

    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
     that
    -1.92
     said
    -1.56
     anderen
    -1.50
     “[
    -1.45
     verschillende
    -1.45
     WHICH
    -1.35
    镠
    -1.34
    媪
    -1.34
     don
    -1.34
     “
    -1.33
    POSITIVE LOGITS
     and
    1.84
    These
    1.76
    Only
    1.65
     responses
    1.62
    Because
    1.59
    with
    1.53
    Perhaps
    1.47
    éricos
    1.47
     ()=>{
    1.43
    Some
    1.42
    Activations Density 0.053%

    No Known Activations