© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 28196
    Prev
    Next
    INDEX
    Explanations

    explicit sexual content

    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
     fibras
    -1.38
     ILLUSTRATIONS
    -1.30
     campeón
    -1.29
    匾
    -1.24
     CHtml
    -1.21
     berlina
    -1.17
     掃除
    -1.15
     or
    -1.14
    ichtig
    -1.13
    頜
    -1.13
    POSITIVE LOGITS
     conocía
    1.21
     рецепта
    1.19
     conoce
    1.13
     trató
    1.07
     conhece
    1.06
     долла
    1.05
     gosta
    1.03
     solicitó
    1.02
    ந்து
    1.01
    辊
    1.01
    Activations Density 0.004%

    No Known Activations