© 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. 10-GEMMASCOPE-RES-131K
    7. 40527
    Prev
    Next
    INDEX
    Explanations

    distance and travel

    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_10/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
     of
    -1.68
    8
    -1.59
    ();
    -1.47
    ”،
    -1.45
    <bos>
    -1.43
     decorativas
    -1.41
     elétrico
    -1.40
    ͇
    -1.35
     always
    -1.34
    我在
    -1.33
    POSITIVE LOGITS
     to
    3.02
     for
    1.62
     разница
    1.52
     prides
    1.52
    +)$
    1.52
     waarschijnlijk
    1.50
    ("")
    1.45
    瑨
    1.44
     respective
    1.42
    pantaloni
    1.40
    Activations Density 0.024%

    No Known Activations