© 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. 35500
    Prev
    Next
    INDEX
    Explanations

    loading this marketplace

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

    `/\_/\` and cat faces

    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
     দার্শনিক
    0.43
     bijoux
    0.43
     значение
    0.42
     cellules
    0.42
    舌
    0.41
    Notation
    0.40
     değişken
    0.40
     defectos
    0.40
     thịt
    0.39
     pikiran
    0.39
    POSITIVE LOGITS
    ano
    0.49
     Oba
    0.48
    loa
    0.47
     Sendai
    0.46
    ที่มี
    0.46
    日曜
    0.46
    ola
    0.45
    m
    0.45
    da
    0.45
     Marrakech
    0.45
    Activations Density 0.000%

    No Known Activations