© 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. 105488
    Prev
    Next
    INDEX
    Explanations

    i'm not sure if

    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
     $
    -1.80
     $\
    -1.69
    )
    -1.63
    </strong>
    -1.59
     которые
    -1.56
     liars
    -1.56
     "
    -1.52
     které
    -1.50
     When
    -1.44
     более
    -1.41
    POSITIVE LOGITS
     lilla
    1.66
     kamb
    1.64
     interventi
    1.57
     campi
    1.54
     saad
    1.53
    糨
    1.51
     will
    1.51
     Borgo
    1.49
     kuna
    1.48
    and
    1.45
    Activations Density 0.014%

    No Known Activations