© 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. 73106
    Prev
    Next
    INDEX
    Explanations

    comment by user

    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
    8
    -1.60
    7
    -1.41
    6
    -1.37
    2
    -1.36
    0
    -1.35
    1
    -1.33
    5
    -1.32
    9
    -1.15
    4
    -1.13
    olesome
    -1.13
    POSITIVE LOGITS
     my
    1.33
     equipada
    1.30
     members
    1.23
    
    1.20
     ‘
    1.17
     своим
    1.17
     entrenar
    1.16
     recently
    1.10
    amon
    1.09
     ventilación
    1.09
    Activations Density 0.033%

    No Known Activations