© 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. 156000
    Prev
    Next
    INDEX
    Explanations

    language, software, and abstract concepts

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

    background or personal qualities

    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
    那么多
    0.53
    ăl
    0.50
    řez
    0.47
    za
    0.47
    urk
    0.46
     knocked
    0.46
     男性用
    0.46
    ’
    0.45
    ahertz
    0.45
    pped
    0.44
    POSITIVE LOGITS
    ᓱ
    0.50
    ㅈ
    0.46
     yür
    0.43
    languages
    0.42
    dining
    0.41
    rification
    0.41
    ियाणा
    0.40
    dinner
    0.40
     incompre
    0.40
     melanin
    0.40
    Activations Density 0.001%

    No Known Activations