© 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. 34-GEMMASCOPE-RES-131K
    7. 1578
    Prev
    Next
    INDEX
    Explanations

    row or rows

    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
    abı
    -0.86
    began
    -0.81
     ¶
    -0.81
    lohn
    -0.80
    actéristiques
    -0.80
    際の
    -0.80
    ￭
    -0.79
    仅仅
    -0.79
    digkeit
    -0.78
     presto
    -0.78
    POSITIVE LOGITS
     Row
    1.96
    Row
    1.92
     row
    1.81
    row
    1.30
     rows
    1.22
    ROW
    1.20
    setRow
    1.07
    Text
    1.05
    Wrap
    1.04
    getRow
    1.02
    Activations Density 0.001%

    No Known Activations