© 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. 111896
    Prev
    Next
    INDEX
    Explanations

    responsibility and information

    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
    quirer
    -1.68
    juries
    -1.62
    therefore
    -1.60
     carteles
    -1.59
    quelles
    -1.53
    rall
    -1.52
    eraard
    -1.51
    SONY
    -1.50
    ngan
    -1.50
     joyería
    -1.50
    POSITIVE LOGITS
     during
    2.02
     
    1.92
     on
    1.88
     provide
    1.84
     for
    1.83
     over
    1.82
     at
    1.79
     R
    1.76
     into
    1.75
     M
    1.74
    Activations Density 0.095%

    No Known Activations