© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 43755
    Prev
    Next
    INDEX
    Explanations

    faces in photographs or abstract patterns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     can
    0.71
    ↵
    0.70
     don
    0.67
    ला
    0.65
     face
    0.57
    )。
    0.56
    ;
    0.53
     το
    0.50
    દ
    0.50
     leash
    0.49
    POSITIVE LOGITS
    os
    0.79
    neurons
    0.65
    datos
    0.64
    aidl
    0.62
    km
    0.61
    that
    0.60
    parser
    0.59
    iça
    0.59
    banks
    0.58
    lardan
    0.57
    Activations Density 0.007%

    No Known Activations