© 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. 234195
    Prev
    Next
    INDEX
    Explanations

    questioning why

    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
    enie
    0.45
    নী
    0.44
    heny
    0.44
    do
    0.44
    eas
    0.43
    pection
    0.43
    나
    0.42
    ↵
    0.42
    nou
    0.41
    ਕ
    0.41
    POSITIVE LOGITS
     ilaç
    0.54
     thuốc
    0.52
     üst
    0.50
     tüket
    0.49
     był
    0.49
     médicament
    0.49
     оказался
    0.48
    ทย์
    0.48
     был
    0.47
     طلبه
    0.47
    Activations Density 0.000%

    No Known Activations