© 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. 14512
    Prev
    Next
    INDEX
    Explanations

    LaTeX document sectioning and counters

    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
     vidéos
    -1.57
     pintadas
    -1.42
     Añade
    -1.42
     但是
    -1.41
     but
    -1.41
    смотрим
    -1.41
    mú
    -1.39
     mencegah
    -1.36
     from
    -1.35
     современ
    -1.32
    POSITIVE LOGITS
    ources
    1.48
    AsUp
    1.43
    atized
    1.43
    ном
    1.42
    ensitive
    1.42
    omeness
    1.41
    atization
    1.40
     anledning
    1.39
     consegui
    1.39
    ()
    1.38
    Activations Density 0.041%

    No Known Activations