© 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. 9419
    Prev
    Next
    INDEX
    Explanations

    я, мы, вы + actions

    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
     of
    -2.73
     it
    -2.69
     they
    -2.17
     każdego
    -2.00
     for
    -1.97
     sehingga
    -1.95
     musíte
    -1.95
     môžete
    -1.91
     naszych
    -1.88
     you
    -1.86
    POSITIVE LOGITS
    EdgeInsets
    2.08
    螃
    1.92
    \
    1.89
    詭
    1.75
     ‘
    1.74
     étendue
    1.72
    ‘’
    1.63
    atother
    1.63
     assise
    1.61
     MotionEvent
    1.59
    Activations Density 0.004%

    No Known Activations