© 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. 58663
    Prev
    Next
    INDEX
    Explanations

    than any other

    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
    鐮
    -1.45
     quantités
    -1.43
    Nuestro
    -1.42
     efekt
    -1.39
    Siempre
    -1.38
    Elles
    -1.34
     preuves
    -1.34
     têtes
    -1.33
     témoignage
    -1.33
     煮
    -1.33
    POSITIVE LOGITS
     this
    1.63
     to
    1.58
     people
    1.44
     ..
    1.38
     time
    1.37
     &
    1.35
     ...
    1.35
     mostly
    1.34
     circumstances
    1.33
    >
    1.32
    Activations Density 0.014%

    No Known Activations