© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 1138
    Prev
    Next
    INDEX
    Explanations

    0 to 1

    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
     włosy
    -1.30
    ensitivity
    -1.28
    </strong>
    -1.24
    hares
    -1.23
     дальней
    -1.21
     tamanho
    -1.21
    ability
    -1.20
    ulence
    -1.20
    ago
    -1.20
     eint
    -1.20
    POSITIVE LOGITS
     to
    2.25
    acağı
    1.38
     one
    1.36
    歐洲
    1.26
     on
    1.26
    gerichte
    1.18
     this
    1.15
     your
    1.15
     yılı
    1.14
     abnormality
    1.14
    Activations Density 0.107%

    No Known Activations