© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101966
    Prev
    Next
    INDEX
    Explanations

    numbers within parentheses

    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
     '
    -2.56
     \\
    -2.02
     }^{
    -1.98
     said
    -1.80
    拶
    -1.78
    collier
    -1.77
     "
    -1.74
    puma
    -1.72
     pierws
    -1.72
    </h3>
    -1.71
    POSITIVE LOGITS
    2
    2.47
    8
    2.42
    5
    2.23
    焢
    2.22
    Some
    2.20
    7
    2.20
    6
    2.17
    From
    2.16
    4
    2.14
    Have
    2.08
    Activations Density 0.090%

    No Known Activations