© 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. 34-GEMMASCOPE-RES-131K
    7. 107224
    Prev
    Next
    INDEX
    Explanations

    photos of myself, out of the way, photos of sets, photos of the dead, pictures of the kids, pictures of Obama, pictures associated with kid, a photo of a blouse, a video of herself, photos of the Solar System, a photo of their food

    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_34/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
     Fotograf
    -1.00
     picture
    -1.00
     photographs
    -0.91
     bildet
    -0.91
    фора
    -0.90
     PHOTOS
    -0.89
    写真
    -0.88
    着一个
    -0.87
    写真の
    -0.87
     needs
    -0.87
    POSITIVE LOGITS
     smiling
    1.20
    実際の
    1.12
    実際に
    1.11
    ACTUAL
    1.08
     from
    0.99
     captioned
    0.97
     underside
    0.97
    請繼續往下閱讀
    0.95
     rosto
    0.94
     bluza
    0.94
    Activations Density 0.065%

    No Known Activations