© 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. 22-GEMMASCOPE-RES-131K
    7. 128438
    Prev
    Next
    INDEX
    Explanations

    data segmentation

    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_22/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
     korrekt
    -1.22
    釓
    -1.19
    人は
    -1.16
     the
    -1.15
     konstant
    -1.05
    ｏ
    -1.04
    Doktor
    -1.03
     isKindOfClass
    -1.03
    する
    -1.02
     службы
    -1.01
    POSITIVE LOGITS
     hetzelfde
    1.13
     Talvez
    1.10
     мә
    1.06
     indescri
    1.06
    将其
    1.05
     creditable
    1.04
     қара
    1.03
     waarmee
    1.03
    合衆
    1.02
     phím
    1.01
    Activations Density 0.119%

    No Known Activations