© 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. 110315
    Prev
    Next
    INDEX
    Explanations

    copyright notices and contact information

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

    discuss wrongdoing, change SSID

    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
     tomb
    0.51
     тю
    0.50
     Tomb
    0.48
    ("/
    0.45
     დაკ
    0.45
    radle
    0.44
    箜
    0.42
    filament
    0.42
    老虎
    0.41
    䒾
    0.41
    POSITIVE LOGITS
    INDIC
    0.51
    AFTER
    0.47
     Varsity
    0.47
    وید
    0.45
     College
    0.44
    OMIC
    0.44
    ولز
    0.43
     college
    0.43
     amici
    0.43
     Diverse
    0.43
    Activations Density 0.002%

    No Known Activations