© 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. 39091
    Prev
    Next
    INDEX
    Explanations

    special symbols and specific words

    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
     What
    -3.09
     When
    -3.05
    </strong>
    -2.88
     Combining
    -2.81
     So
    -2.80
     These
    -2.78
     Not
    -2.72
     How
    -2.66
     Creating
    -2.61
     excellent
    -2.52
    POSITIVE LOGITS
    蠖
    2.70
    actéristi
    2.48
    饹
    2.39
    殽
    2.39
    鹩
    2.34
     quintessential
    2.33
     frère
    2.20
     pn
    2.20
    铤
    2.17
     gouverneur
    2.16
    Activations Density 0.000%

    No Known Activations