© 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. 95851
    Prev
    Next
    INDEX
    Explanations

    relationships, problems, ownership

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

    sound, high, taste, found, scarred, driven

    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
    *,
    0.52
     ซึ่ง
    0.47
     ทำให้
    0.46
     Makes
    0.46
    "),
    0.46
    stringstream
    0.45
     trochę
    0.45
    .");
    0.44
    ვი
    0.44
     쓰는
    0.43
    POSITIVE LOGITS
     ремо
    0.49
     ставка
    0.49
     проблема
    0.48
    его
    0.48
    Dep
    0.47
     стадии
    0.46
    Deaths
    0.46
    два
    0.46
     ремонта
    0.46
     голо
    0.46
    Activations Density 0.001%

    No Known Activations