© 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. 111427
    Prev
    Next
    INDEX
    Explanations

    get + something

    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
     “
    -1.66
     we
    -1.41
     ‘
    -1.30
     erhalten
    -1.23
    ↵
    -1.20
     brilh
    -1.18
    before
    -1.15
    lication
    -1.10
     diversas
    -1.09
     or
    -1.09
    POSITIVE LOGITS
    תודה
    1.51
    tuous
    1.38
     didik
    1.36
     Popis
    1.34
     serca
    1.30
    всем
    1.28
    isiert
    1.27
     Février
    1.27
    '}}
    1.27
     段
    1.26
    Activations Density 0.024%

    No Known Activations