© 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. 46193
    Prev
    Next
    INDEX
    Explanations

    beautiful summer season

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

    foreign/uncommon words

    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
     됐다
    0.46
    Executives
    0.44
    call
    0.42
    apprentissage
    0.42
    Compute
    0.41
     ಅಂ
    0.41
    诀
    0.41
    쫄
    0.39
    pump
    0.39
    狗
    0.39
    POSITIVE LOGITS
     okt
    0.56
     klasy
    0.54
     suspects
    0.52
     escribir
    0.52
    rana
    0.51
     naj
    0.50
    например
    0.49
    reta
    0.49
     držav
    0.49
     eliminar
    0.48
    Activations Density 0.000%

    No Known Activations