© 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. 67811
    Prev
    Next
    INDEX
    Explanations

    artistic interpretation or rendition

    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
    \
    -1.69
     When
    -1.66
     In
    -1.65
    骉
    -1.64
    Ἢ
    -1.63
     Even
    -1.59
    cellor
    -1.58
     at
    -1.58
    行了
    -1.57
    筏
    -1.55
    POSITIVE LOGITS
     ‘’
    1.66
    鲠
    1.54
     puramente
    1.48
     maso
    1.47
     zorro
    1.45
    лення
    1.44
    טה
    1.41
    嘸
    1.40
     

    1.40
     asseg
    1.38
    Activations Density 0.034%

    No Known Activations