© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 23922
    Prev
    Next
    INDEX
    Explanations

    let, suppose, deduce, permission

    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
    tujuan
    -1.04
     متعلقه
    -1.02
     príncipe
    -0.95
    ੯
    -0.94
    itados
    -0.90
    pierw
    -0.88
    Tomb
    -0.85
     této
    -0.85
    Če
    -0.85
     失
    -0.84
    POSITIVE LOGITS
    <u>
    0.91
     especially
    0.90
    <strong>
    0.90
    <em>
    0.85
     conclusion
    0.84
    …
    0.83
    _
    0.81
    Originally
    0.80
    ,
    0.80
    Referenties
    0.79
    Activations Density 0.001%

    No Known Activations