© 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. 127729
    Prev
    Next
    INDEX
    Explanations

    jumper motorbike racing

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

    entrepreneurial venture, databases, racist acts

    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
    They
    0.49
     They
    0.47
    encher
    0.46
    someone
    0.45
    ਵ
    0.45
    ją
    0.44
    utes
    0.43
     सिद्धांत
    0.43
    zuk
    0.43
    vät
    0.43
    POSITIVE LOGITS
     ưu
    0.48
     boolean
    0.46
     myeloid
    0.46
     sequential
    0.44
     nt
    0.41
     Abdullah
    0.41
     cho
    0.41
     postural
    0.41
    );\
    0.41
     nửa
    0.40
    Activations Density 0.001%

    No Known Activations