© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13260
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

    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
     also
    -1.89
     the
    -1.64
    beta
    -1.55
     andere
    -1.45
     into
    -1.30
     other
    -1.29
    other
    -1.27
    and
    -1.26
    </h4>
    -1.25
     nomme
    -1.22
    POSITIVE LOGITS
     éste
    1.31
    }}]{
    1.27
     jį
    1.23
     njego
    1.22
    cyjnych
    1.20
    新たな
    1.20
    縹
    1.20
    荑
    1.19
     ihtiyaç
    1.19
    jutant
    1.19
    Activations Density 0.065%

    No Known Activations