© 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. 57636
    Prev
    Next
    INDEX
    Explanations

    finding pairs by complement

    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
    <0x06>
    0.44
    цо
    0.39
    ισμού
    0.39
    со
    0.38
    ко
    0.37
     berita
    0.37
    igration
    0.37
     disaster
    0.37
     便
    0.37
    үкт
    0.37
    POSITIVE LOGITS
    alary
    0.47
     Examin
    0.47
     Screening
    0.46
     स्क्रीनिंग
    0.45
     encompass
    0.42
    elling
    0.42
     Indices
    0.41
    报考
    0.41
     sınav
    0.41
     Exam
    0.40
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.