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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 630
    Prev
    Next
    INDEX
    Explanations

    P.O. Box and P.C

    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
    </h2>
    -2.58
    </b>
    -2.17
    </sup>
    -1.79
    those
    -1.45
    you
    -1.45
    ()))
    -1.43
     diseñados
    -1.40
    3
    -1.37
     poziomie
    -1.36
    which
    -1.32
    POSITIVE LOGITS
     to
    1.66
    木材
    1.45
    ardoor
    1.38
    лил
    1.32
    :{
    1.32
    corrosion
    1.31
    embroidered
    1.28
     rallies
    1.28
     ospiti
    1.27
     Paradox
    1.27
    Activations Density 0.033%

    No Known Activations