© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70800
    Prev
    Next
    INDEX
    Explanations

    veteran or opt-in before certain actions/events

    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
     Those
    -1.56
     Why
    -1.52
    .”
    -1.41
     now
    -1.41
     Some
    -1.39
     Hundreds
    -1.38
     Others
    -1.34
    々な
    -1.34
     While
    -1.28
     reparar
    -1.27
    POSITIVE LOGITS
    </b>
    1.83
    ſche
    1.59
    </h5>
    1.55
    ISING
    1.50
     importante
    1.50
     REVIEW
    1.50
    ༔
    1.49
     echa
    1.48
     แ
    1.48
    ">'+
    1.48
    Activations Density 0.148%

    No Known Activations