© 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. 79773
    Prev
    Next
    INDEX
    Explanations

    infliximab molecule

    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
    。。
    0.44
     Örneğin
    0.43
     Merkez
    0.43
    高志森
    0.42
    scrollHeight
    0.41
    itemconfig
    0.40
     Engineers
    0.39
     及
    0.39
    વવા
    0.39
    fertigt
    0.39
    POSITIVE LOGITS
     averiguar
    0.45
     rhythms
    0.45
    روج
    0.44
     način
    0.42
    hren
    0.42
     atras
    0.41
    ଞ
    0.41
     espaces
    0.41
     lehetős
    0.41
     llamada
    0.40
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.