© 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. 127924
    Prev
    Next
    INDEX
    Explanations

    optical technology and related concepts

    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
     to
    -2.05
    顳
    -2.02
     and
    -1.97
    >
    -1.95
     kemudian
    -1.88
     with
    -1.84
     процес
    -1.81
    一是
    -1.80
     (‘
    -1.78
    ࣭
    -1.76
    POSITIVE LOGITS
    </h3>
    2.56
    色の
    2.03
     перспекти
    1.98
    憷
    1.96
    --
    1.95
     truthful
    1.94
    rógeno
    1.91
    1.88
    茛
    1.88
    л
    1.88
    Activations Density 0.039%

    No Known Activations