© 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. 44905
    Prev
    Next
    INDEX
    Explanations

    creating HTML elements

    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
     to
    -2.02
     Deinen
    -1.62
    ING
    -1.62
    7
    -1.59
    S
    -1.55
    Its
    -1.54
     employees
    -1.52
    1
    -1.52
     garantiert
    -1.49
     allmäh
    -1.45
    POSITIVE LOGITS
     graciosos
    1.84
     adornos
    1.55
     cejas
    1.51
     oreille
    1.51
     religieuses
    1.50
     costuras
    1.49
    kunjung
    1.48
     botella
    1.46
    Алек
    1.45
     sabias
    1.43
    Activations Density 0.004%

    No Known Activations