© 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. 34-GEMMASCOPE-RES-131K
    7. 77975
    Prev
    Next
    INDEX
    Explanations

    documents and correspondence

    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_34/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
     documento
    -1.17
     Downloads
    -1.09
     DOCUMENT
    -1.06
     paragraphe
    -1.01
     Presented
    -0.97
     gelas
    -0.96
     onData
    -0.96
    虓
    -0.96
    fordable
    -0.95
     rollen
    -0.95
    POSITIVE LOGITS
     list
    1.62
     photographs
    1.41
     photograph
    1.27
     letter
    1.23
     photos
    1.21
     schedule
    1.19
     financial
    1.12
     agreements
    1.12
     correspondence
    1.10
     completed
    1.08
    Activations Density 0.036%

    No Known Activations