© 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. 117179
    Prev
    Next
    INDEX
    Explanations

    common conjunctions and lists

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

    performance degradation or latency

    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
    VING
    0.52
     Parent
    0.48
    هاي
    0.47
     Diabetic
    0.46
    Parent
    0.45
    鑄
    0.45
     وين
    0.45
    VIR
    0.44
    LE
    0.43
     reluct
    0.43
    POSITIVE LOGITS
    iseta
    0.56
    itius
    0.51
    ۵
    0.47
    ukuoka
    0.46
    qtd
    0.44
    berapa
    0.43
     কাহার
    0.43
     pertumbuhan
    0.43
    etrot
    0.43
    ítez
    0.43
    Activations Density 0.001%

    No Known Activations