© 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. 18868
    Prev
    Next
    INDEX
    Explanations

    to the

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

    articles and prepositions

    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
    rá
    0.68
    a
    0.64
    ه
    0.61
     。,
    0.60
     člen
    0.60
     atualizar
    0.60
     setzt
    0.57
     щоб
    0.57
    。
    0.57
     IComparable
    0.56
    POSITIVE LOGITS
     the
    1.03
     a
    0.89
    the
    0.84
     have
    0.82
    The
    0.80
    기
    0.79
     their
    0.76
    ppled
    0.75
     this
    0.73
    A
    0.73
    Activations Density 0.515%

    No Known Activations