© 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. 15110
    Prev
    Next
    INDEX
    Explanations

    officially released or conditional statements

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

    structured lists and delimiters

    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
    ла
    0.73
    си
    0.69
    conto
    0.61
    ת
    0.59
    ри
    0.58
    에
    0.58
     với
    0.57
     wholeheartedly
    0.57
    Más
    0.55
    ð
    0.55
    POSITIVE LOGITS
     lLoginID
    0.64
    শংস
    0.63
     kanamycin
    0.61
     unsere
    0.58
    পর্য
    0.58
    閡
    0.57
     qRT
    0.56
     Auswirkungen
    0.55
    anganese
    0.55
     ஆய்வு
    0.55
    Activations Density 0.000%

    No Known Activations