© 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. 96597
    Prev
    Next
    INDEX
    Explanations

    language fragment association

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

    listing examples

    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
    ros
    0.49
    يس
    0.45
    這樣的
    0.44
    uk
    0.43
    effects
    0.43
    導數
    0.42
    來
    0.42
    說是
    0.41
    ৯
    0.41
    lens
    0.41
    POSITIVE LOGITS
     planification
    0.46
    頚
    0.46
     değişik
    0.46
    چھا
    0.45
     gerekiyor
    0.45
    ❣
    0.44
    artment
    0.44
    GraphQl
    0.44
     dolayı
    0.43
    צוני
    0.43
    Activations Density 0.001%

    No Known Activations