© 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. 10-GEMMASCOPE-RES-131K
    7. 128165
    Prev
    Next
    INDEX
    Explanations

    causes, compositions, and effects

    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
    另一
    -1.54
    瑧
    -1.51
    嗥
    -1.46
    ܃
    -1.41
    oczes
    -1.40
     loue
    -1.39
    ÜN
    -1.36
     made
    -1.35
     tramontina
    -1.34
     beft
    -1.34
    POSITIVE LOGITS
     to
    2.20
    𖥧
    1.85
     beider
    1.72
     folgen
    1.59
    achute
    1.58
     podrá
    1.53
     THEIR
    1.49
    ípio
    1.48
     gemessen
    1.48
     creativa
    1.47
    Activations Density 0.207%

    No Known Activations