© 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. 73211
    Prev
    Next
    INDEX
    Explanations

    academic or technical problems

    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
    ům
    -1.61
    鹇
    -1.55
     มา
    -1.53
    怎么回事
    -1.51
    および
    -1.39
     was
    -1.38
    ，「
    -1.36
    ’
    -1.31
    quần
    -1.30
    =""
    -1.30
    POSITIVE LOGITS
    </strong>
    1.52
    нім
    1.46
     вона
    1.37
    誑
    1.36
     BOTH
    1.35
     in
    1.34
     задач
    1.34
     passenden
    1.32
    鏵
    1.31
     dacă
    1.30
    Activations Density 0.053%

    No Known Activations