© 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. 73624
    Prev
    Next
    INDEX
    Explanations

    technical terms and code snippets

    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
     and
    -1.73
    ֠
    -1.35
     on
    -1.30
    </h3>
    -1.30
     eigentliche
    -1.26
     any
    -1.23
     when
    -1.22
     after
    -1.22
     cualquier
    -1.18
    せずに
    -1.18
    POSITIVE LOGITS
    those
    1.72
     bén
    1.45
    ayant
    1.36
    However
    1.33
     kosten
    1.32
     normaux
    1.30
     remarqu
    1.27
    埴
    1.27
     促销
    1.27
     halten
    1.26
    Activations Density 0.265%

    No Known Activations