© 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. 58488
    Prev
    Next
    INDEX
    Explanations

    AV followed by terms

    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
    ้อง
    -0.87
    Namaste
    -0.82
    Bata
    -0.80
    ואר
    -0.80
    Paradox
    -0.80
     cucchia
    -0.77
    Schedules
    -0.73
    Modifying
    -0.73
     Vespa
    -0.72
    纹
    -0.72
    POSITIVE LOGITS
    Av
    1.22
     Av
    1.09
     AV
    1.04
     av
    1.01
    GroupLayout
    0.91
    awt
    0.88
    AV
    0.83
    ➷
    0.83
     Liber
    0.82
    lioma
    0.82
    Activations Density 0.041%

    No Known Activations