© 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. 8397
    Prev
    Next
    INDEX
    Explanations

    serving others or society

    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
     hvit
    -1.59
     hjemmeside
    -1.52
     ferdig
    -1.51
    kwür
    -1.48
    Tapi
    -1.48
    ～♪
    -1.47
     beliebt
    -1.47
     往
    -1.46
     Insets
    -1.42
    ᷇
    -1.42
    POSITIVE LOGITS
    us
    2.14
    will
    1.90
    <i>
    1.90
     tidak
    1.88
     zarówno
    1.81
     to
    1.78
    We
    1.70
     grafica
    1.67
    铪
    1.63
     Unfortunately
    1.56
    Activations Density 0.023%

    No Known Activations