© 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. 22-GEMMASCOPE-RES-131K
    7. 25548
    Prev
    Next
    INDEX
    Explanations

    structured data and metadata

    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_22/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
     if
    -2.03
    Beskrivning
    -1.91
    ☫
    -1.72
    The
    -1.70
    ̗
    -1.67
     作り方
    -1.67
    Despite
    -1.66
    Новые
    -1.64
    Приготовление
    -1.64
    ции
    -1.64
    POSITIVE LOGITS
     keo
    1.81
    -
    1.79
    蟊
    1.72
    {
    1.71
    儅
    1.70
    ’
    1.69
     betreffende
    1.62
    臵
    1.62
    _
    1.62
    きち
    1.61
    Activations Density 0.004%

    No Known Activations