© 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. 11980
    Prev
    Next
    INDEX
    Explanations

    if any or no

    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
    {
    -1.48
    \
    -1.47
    .
    -1.41
    ]
    -1.41
    |+
    -1.38
    ḇ
    -1.38
     extraordin
    -1.23
     sovi
    -1.22
    涜
    -1.20
    ched
    -1.17
    POSITIVE LOGITS
     templado
    1.35
     zwanzig
    1.33
     verantwort
    1.31
     unseres
    1.30
     ausgesprochen
    1.27
    都不是
    1.27
     redaktion
    1.25
     peligroso
    1.24
     erlä
    1.23
    ﺶ
    1.22
    Activations Density 0.017%

    No Known Activations