© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 75026
    Prev
    Next
    INDEX
    Explanations

    photo and pictures

    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
     $
    -1.18
    tvrt
    -1.13
     or
    -1.12
     to
    -1.06
     MediatR
    -1.03
    ләр
    -1.01
    მ
    -1.01
    也能
    -1.00
    एस
    -0.99
    不宜
    -0.99
    POSITIVE LOGITS
     photos
    1.49
     photo
    1.34
    📸
    1.21
     toilettes
    1.17
    Still
    1.15
    📷
    1.14
     jati
    1.13
     recomand
    1.13
    帐户
    1.13
     photographs
    1.10
    Activations Density 0.043%

    No Known Activations