© 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. 53572
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by nouns

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

    technical prompts and queries

    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
    ეც
    0.43
    oguć
    0.43
    getahuan
    0.43
    appelijke
    0.43
    hehi
    0.42
    geoning
    0.42
    hitva
    0.40
    ા
    0.40
    aints
    0.40
     కార్య
    0.39
    POSITIVE LOGITS
     criteri
    0.52
     litmus
    0.52
     riguardo
    0.50
     параметра
    0.46
     parameter
    0.46
     regards
    0.46
     searches
    0.45
     queries
    0.44
     desafio
    0.44
     automated
    0.44
    Activations Density 0.106%

    No Known Activations