© 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. 8766
    Prev
    Next
    INDEX
    Explanations

    system

    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
    trauer
    -1.49
     nessuno
    -1.48
     for
    -1.47
    ˕
    -1.46
     the
    -1.46
     særlig
    -1.42
     œufs
    -1.42
    泔
    -1.40
    pdata
    -1.38
     decisione
    -1.38
    POSITIVE LOGITS
    (
    2.06
    C
    1.77
    m
    1.69
    圌
    1.64
     
    1.64
    at
    1.63
    </
    1.62
     kjer
    1.60
    on
    1.58
    </h4>
    1.55
    Activations Density 0.022%

    No Known Activations