© 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. 95643
    Prev
    Next
    INDEX
    Explanations

    foreign named entities

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

    Clark noticedallowing authentication

    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
    iy
    0.52
    itol
    0.48
    root
    0.47
    survival
    0.47
    shel
    0.45
    igl
    0.45
    ft
    0.44
    s
    0.44
    ipple
    0.44
    instead
    0.44
    POSITIVE LOGITS
     Engagement
    0.53
     Hala
    0.52
     adlı
    0.52
     Zeichen
    0.49
     Principal
    0.49
     Tuc
    0.49
     Bokeh
    0.49
     Badajoz
    0.49
     Sempre
    0.48
     Praia
    0.48
    Activations Density 0.001%

    No Known Activations