© 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. 241780
    Prev
    Next
    INDEX
    Explanations

    after certain words

    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
    ᅧ
    0.50
    vind
    0.48
    rectionType
    0.47
    ોર્ટ
    0.47
     ಫಲ
    0.47
    vino
    0.46
    vertices
    0.46
    gado
    0.45
    vindos
    0.45
    𝙪
    0.45
    POSITIVE LOGITS
     seçenek
    0.46
    蔑
    0.42
     Pleasant
    0.41
    文件夹
    0.40
     Portable
    0.40
    发言
    0.40
    诸多
    0.39
     sö
    0.39
     rabbit
    0.39
     系统
    0.39
    Activations Density 0.000%

    No Known Activations