© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 31293
    Prev
    Next
    INDEX
    Explanations

    shepherd

    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
    an
    1.68
    t
    1.42
    нг
    1.38
    p
    1.27
    l
    1.26
    im
    1.23
    u
    1.20
    ar
    1.06
    as
    1.05
    é
    1.04
    POSITIVE LOGITS
     in
    1.25
     shepherd
    1.20
     Shepherd
    1.16
    大海
    0.95
     morning
    0.93
    కు
    0.91
     point
    0.88
     pastor
    0.86
     loan
    0.85
     son
    0.84
    Activations Density 0.001%

    No Known Activations