© 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. 181994
    Prev
    Next
    INDEX
    Explanations

    possessive followed by noun

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

    religion, relationships, and lists

    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
     מא
    0.50
     శు
    0.48
     马
    0.47
    ри
    0.46
    偽
    0.45
     খেলার
    0.45
     розгля
    0.45
    电路
    0.45
    deren
    0.44
     בדי
    0.44
    POSITIVE LOGITS
    م
    0.54
     Argentina
    0.53
     internacional
    0.51
     fossils
    0.51
     insegn
    0.51
     replicate
    0.51
     conifers
    0.51
     iconic
    0.50
    IVES
    0.50
     beras
    0.50
    Activations Density 0.000%

    No Known Activations