© 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. 29193
    Prev
    Next
    INDEX
    Explanations

    declaring data types and properties

    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
    这个
    0.46
    这是一
    0.43
    Exporter
    0.43
    的是
    0.42
    然后在
    0.42
    프
    0.42
    S
    0.41
    ό
    0.41
    С
    0.41
    üğ
    0.41
    POSITIVE LOGITS
     forts
    0.47
     pals
    0.46
     भोग
    0.46
     गांव
    0.46
     employ
    0.45
     διαφορε
    0.45
     कोड
    0.44
    ករណ៍
    0.44
     bety
    0.44
     कोणत्याही
    0.44
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.