© 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. 98636
    Prev
    Next
    INDEX
    Explanations

    foreign language words

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

    bulleted lists for emphasis

    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
    ەتی
    0.51
    淈
    0.51
    ictured
    0.49
    idir
    0.49
    aih
    0.48
    桝
    0.48
    uci
    0.47
    ℑ
    0.47
    ibili
    0.46
     scaleOf
    0.46
    POSITIVE LOGITS
     tête
    0.47
    {~
    0.44
     contagion
    0.43
     كن
    0.42
     muerte
    0.41
    chuk
    0.41
     constante
    0.39
     كمان
    0.39
    -
    0.39
     большин
    0.39
    Activations Density 0.002%

    No Known Activations