© 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. 109761
    Prev
    Next
    INDEX
    Explanations

    common word followed by specific word

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

    error budget downtime

    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
     olio
    0.50
    ８
    0.45
    ５
    0.44
     автомобиль
    0.43
     에게
    0.42
     новая
    0.41
    eno
    0.41
     छवि
    0.41
    лово
    0.40
     colleague
    0.39
    POSITIVE LOGITS
    тын
    0.45
    ran
    0.45
     المؤ
    0.44
    get
    0.44
    阏
    0.43
     susceptibles
    0.43
     Empresa
    0.42
    frac
    0.42
     العام
    0.41
    膣
    0.41
    Activations Density 0.001%

    No Known Activations