© 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. 49250
    Prev
    Next
    INDEX
    Explanations

    Brooklyn Bridge

    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
    خلي
    0.75
    اي
    0.66
    S
    0.65
    ER
    0.64
    رق
    0.64
    {
    0.64
    τ
    0.63
    surname
    0.63
    و
    0.63
    是因为
    0.60
    POSITIVE LOGITS
    -
    0.79
     propagation
    0.77
     pubescent
    0.72
     enhancement
    0.71
     illumination
    0.71
     Brooklyn
    0.70
     endorsement
    0.70
     augmentation
    0.69
     אחד
    0.67
     activating
    0.67
    Activations Density 0.002%

    No Known Activations