© 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. 201366
    Prev
    Next
    INDEX
    Explanations

    site by, Sunday league, access to

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

    legal, ACA, influenced, loans, documents

    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
     rabbis
    0.50
    AreaData
    0.47
    <unused28>
    0.46
    NavBar
    0.46
    RationalValue
    0.46
     zahval
    0.45
     छिपा
    0.44
     शू
    0.44
     छुपा
    0.44
     நாள்
    0.44
    POSITIVE LOGITS
    sh
    0.52
    g
    0.52
    ори
    0.50
    c
    0.48
    mo
    0.46
    ian
    0.46
    emics
    0.46
     Alfred
    0.46
    ه
    0.45
    bling
    0.45
    Activations Density 0.001%

    No Known Activations