© 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. 208886
    Prev
    Next
    INDEX
    Explanations

    sequences followed by conjunctions or prepositions

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

    consult doctor/médico/embassy

    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
     personnalisé
    0.52
     продукции
    0.49
    诬
    0.49
    Longrightarrow
    0.48
     компью
    0.48
    庆祝
    0.48
    潘
    0.47
    ِمض
    0.46
    DataXYZ
    0.45
    kiej
    0.45
    POSITIVE LOGITS
     which
    0.54
     e
    0.53
     silo
    0.53
     t
    0.51
     Vy
    0.51
     vy
    0.50
     pixel
    0.50
    μένος
    0.49
    גד
    0.48
     line
    0.46
    Activations Density 0.000%

    No Known Activations