© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103450
    Prev
    Next
    INDEX
    Explanations

    small or large sizes

    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
    мона
    -1.74
     volumen
    -1.59
    笕
    -1.54
     on
    -1.52
     extraordin
    -1.47
    Ǝ
    -1.45
     when
    -1.45
    ❔
    -1.44
    </h3>
    -1.43
     ilegal
    -1.42
    POSITIVE LOGITS
     zostały
    1.63
     verkau
    1.61
     Kindern
    1.59
     hormigón
    1.58
     the
    1.56
     eigenen
    1.55
     eigenes
    1.55
     feiner
    1.53
     Produkten
    1.52
     ogrom
    1.48
    Activations Density 0.015%

    No Known Activations