© 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. 25704
    Prev
    Next
    INDEX
    Explanations

    population characteristics

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

    whose properties or components

    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
     гара
    0.55
    ләү
    0.52
    Ordenar
    0.51
     ૨
    0.50
    Logout
    0.50
    Reduce
    0.48
     восем
    0.47
    在一个
    0.47
    BufferedReader
    0.47
    এবং
    0.47
    POSITIVE LOGITS
     metastable
    0.57
     which
    0.53
     whose
    0.49
     whence
    0.48
     (>
    0.46
     devi
    0.45
     inclusiv
    0.45
     inasmuch
    0.45
    despite
    0.44
    INCLUDING
    0.44
    Activations Density 0.000%

    No Known Activations