© 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. 7247
    Prev
    Next
    INDEX
    Explanations

    compounds and followed nouns

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

    city, luxury, craft, history, religion

    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
    শিংটন
    0.33
     cái
    0.33
    ৈতিক
    0.32
     nhưng
    0.32
    echolog
    0.32
     থাকে
    0.31
    <unused52>
    0.30
     但是
    0.30
    atthena
    0.29
     ruangan
    0.29
    POSITIVE LOGITS
     S
    0.42
    1
    0.40
    S
    0.40
     T
    0.39
     and
    0.39
     World
    0.37
     Family
    0.37
     Science
    0.36
     D
    0.36
    -
    0.36
    Activations Density 0.000%

    No Known Activations