© 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. 92803
    Prev
    Next
    INDEX
    Explanations

    words like "herein," "heretofore," "hereinbelow," "hereinafter"

    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
     אחרים
    -0.88
     volto
    -0.81
    honey
    -0.81
     milano
    -0.80
     idiota
    -0.79
     clinica
    -0.79
    kenal
    -0.75
     verdure
    -0.75
     PROSPECT
    -0.75
     miele
    -0.75
    POSITIVE LOGITS
    下的
    1.13
    前的
    1.05
    下
    1.00
    후
    0.94
    外的
    0.88
    後
    0.86
     berth
    0.83
    переди
    0.78
    後の
    0.78
    后的
    0.78
    Activations Density 0.021%

    No Known Activations