© 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. 103287
    Prev
    Next
    INDEX
    Explanations

    parts and related entities

    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
    urns
    -1.48
    砗
    -1.48
     perquè
    -1.48
    .
    -1.47
     kertoo
    -1.41
     võib
    -1.41
     -->
    -1.41
     continúas
    -1.40
     pelúcia
    -1.40
     convertView
    -1.38
    POSITIVE LOGITS
     are
    2.33
     then
    1.87
     will
    1.81
    h
    1.55
     would
    1.43
     need
    1.39
     cannot
    1.36
    Then
    1.34
     have
    1.32
     must
    1.31
    Activations Density 0.090%

    No Known Activations