© 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. 30485
    Prev
    Next
    INDEX
    Explanations

    metadata fields: author, date, license, type

    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
    DESCRIPTION
    -2.02
     description
    -1.97
    Description
    -1.96
     Description
    -1.92
     DESCRIPTION
    -1.91
     descriptions
    -1.82
    descripcion
    -1.81
     описа
    -1.80
     described
    -1.79
    description
    -1.74
    POSITIVE LOGITS
     keywords
    0.98
     long
    0.95
     how
    0.89
    ละเอ
    0.88
     How
    0.88
     examples
    0.85
    alignItems
    0.84
     links
    0.82
     warnings
    0.79
    How
    0.78
    Activations Density 0.056%

    No Known Activations