© 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. 99427
    Prev
    Next
    INDEX
    Explanations

    culinary measurements

    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
    moiselle
    -1.52
    蟜
    -1.51
     outubro
    -1.51
    prender
    -1.48
    嫱
    -1.41
    鶯
    -1.39
    diye
    -1.38
     okolo
    -1.38
     chicas
    -1.38
    usions
    -1.38
    POSITIVE LOGITS
    5
    1.70
    jenige
    1.58
     such
    1.56
    ).
    1.55
    o
    1.55
    ."
    1.53
    没了
    1.46
    うれ
    1.41
    }$.
    1.41
    Such
    1.38
    Activations Density 0.005%

    No Known Activations