© 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. 43839
    Prev
    Next
    INDEX
    Explanations

    symbols then words

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

    majority, all, important

    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
     yaşında
    0.45
    의
    0.45
     và
    0.44
    로
    0.44
     crore
    0.44
     couvertures
    0.44
    0
    0.44
    ＋
    0.43
    /
    0.43
    ৰ
    0.43
    POSITIVE LOGITS
    ütte
    0.45
     ప్రస్తుతం
    0.43
     Publikum
    0.42
     имени
    0.41
     ਇਹ
    0.41
     Союз
    0.41
     председа
    0.40
    comer
    0.40
    mittedly
    0.40
    弑
    0.40
    Activations Density 0.003%

    No Known Activations