© 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. 131976
    Prev
    Next
    INDEX
    Explanations

    Polish names or nationalities

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

    Leadership, people, years, early, baby

    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
     diminue
    0.52
    阐
    0.51
    literal
    0.51
    nonzero
    0.50
     ออก
    0.49
     spécialement
    0.48
     तुल
    0.47
    liv
    0.46
     déprimées
    0.46
     réfléch
    0.46
    POSITIVE LOGITS
     Akbar
    0.50
     Megh
    0.46
     marad
    0.45
     Mendes
    0.44
     Derek
    0.44
     M
    0.44
     assemblies
    0.42
     Rails
    0.42
     items
    0.42
     crowned
    0.42
    Activations Density 0.002%

    No Known Activations