© 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. 66569
    Prev
    Next
    INDEX
    Explanations

    high school, smuggling cartel, Island Baby

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

    ticket numbers

    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
     услуг
    0.44
    움
    0.43
    Biscuit
    0.42
    EndPoint
    0.41
     श्रीवास्तव
    0.41
     Priyanka
    0.41
    着
    0.41
    拿
    0.39
    呦
    0.39
    ന്ധി
    0.39
    POSITIVE LOGITS
     radionu
    0.52
     oligodend
    0.52
    peng
    0.52
     orient
    0.51
     symplect
    0.50
    நர்
    0.48
     Anosov
    0.48
     inhom
    0.48
     sistemas
    0.47
     écrite
    0.47
    Activations Density 0.000%

    No Known Activations