© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 164827
    Prev
    Next
    INDEX
    Explanations

    distorting images

    np_acts-logits-general · gemini-2.5-flash-lite

    aspect ratio

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    را
    0.59
    '\
    0.57
     de
    0.50
    “
    0.48
    star
    0.48
     mux
    0.47
     seg
    0.45
    "
    0.45
    وة
    0.45
    '%
    0.45
    POSITIVE LOGITS
     велосипе
    0.57
     дорога
    0.49
     소녀
    0.49
     сестра
    0.48
    ጒ
    0.48
    bicycle
    0.47
    apayati
    0.47
     தாய்
    0.47
     السيارة
    0.47
    atthena
    0.46
    Activations Density 0.001%

    No Known Activations