© 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. 158470
    Prev
    Next
    INDEX
    Explanations

    USD, Ltd, usable

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

    words after certain types of words

    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
     picnics
    0.46
     bijna
    0.46
     resellers
    0.45
     truckers
    0.45
    浾
    0.44
     menawarkan
    0.43
     descuento
    0.42
    还能
    0.42
     pengunjung
    0.42
     ponsel
    0.41
    POSITIVE LOGITS
    >.
    0.49
    \
    0.41
     <
    0.39
     psycho
    0.39
    羁
    0.38
    Throughout
    0.38
     தொடர்பாக
    0.38
     insofar
    0.37
     psychologically
    0.37
     περίπτωση
    0.37
    Activations Density 0.001%

    No Known Activations