© 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. 40913
    Prev
    Next
    INDEX
    Explanations

    property of

    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
    KommentareTeilen
    -2.03
    鸶
    -1.72
    -\\
    -1.66
    tored
    -1.61
    が使
    -1.61
    嬲
    -1.60
     Ã
    -1.58
    onnaise
    -1.56
     帅气
    -1.54
    を活用
    -1.52
    POSITIVE LOGITS
    7
    2.31
    3
    2.27
    8
    2.16
    4
    2.05
    6
    2.03
    2
    1.99
    Despite
    1.91
    9
    1.91
    5
    1.90
    and
    1.79
    Activations Density 0.031%

    No Known Activations