© 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. 192148
    Prev
    Next
    INDEX
    Explanations

    viagra and poker

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

    modelling, regulation, and control systems

    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
     covering
    0.47
     „
    0.46
     jam
    0.46
     </
    0.45
     overw
    0.44
     overwrite
    0.44
     deformity
    0.43
     Cove
    0.42
     Brill
    0.42
     ?-
    0.42
    POSITIVE LOGITS
     pubblica
    0.50
    ASIA
    0.44
    ugeot
    0.44
    UEST
    0.43
    spolit
    0.43
    aec
    0.42
    ۽
    0.42
    ssia
    0.42
     sugi
    0.41
    🕎
    0.41
    Activations Density 0.001%

    No Known Activations