© 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. 85676
    Prev
    Next
    INDEX
    Explanations

    beard and chin

    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
     correos
    -1.45
     accompagner
    -1.45
     declaração
    -1.36
     CALIFOR
    -1.31
     ốp
    -1.24
    廔
    -1.23
    paign
    -1.23
     opinião
    -1.21
    "}"
    -1.21
    onder
    -1.20
    POSITIVE LOGITS
     Facial
    1.21
     or
    1.19
     using
    1.18
     bearded
    1.18
     facial
    1.17
     \\
    1.13
    ｧ
    1.13
     Re
    1.10
     से
    1.10
     re
    1.09
    Activations Density 0.065%

    No Known Activations