© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 42782
    Prev
    Next
    INDEX
    Explanations

    break, broken, breaking

    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
    uña
    0.64
    ו
    0.64
    л
    0.61
    หลด
    0.59
    tong
    0.59
    еры
    0.59
    führung
    0.59
     techno
    0.58
    сите
    0.58
     хи
    0.57
    POSITIVE LOGITS
    ir
    0.62
    v
    0.60
    Field
    0.60
    Fragment
    0.57
     I
    0.56
    ETTE
    0.55
    4
    0.54
     smash
    0.54
     B
    0.54
    Name
    0.54
    Activations Density 0.018%

    No Known Activations