© 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. 242108
    Prev
    Next
    INDEX
    Explanations

    hyphenated compounds

    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
    㳒
    0.54
    秇
    0.53
    参数向量
    0.53
    揾
    0.49
    DefinitionGroup
    0.48
    ıyor
    0.47
    枒
    0.47
    تاء
    0.47
    稆
    0.47
    اؤن
    0.46
    POSITIVE LOGITS
    a
    0.51
    。
    0.49
    0.47
    i
    0.46
     frowned
    0.44
     CSS
    0.43
     zbyt
    0.43
     dokument
    0.43
    o
    0.43
    ὑ
    0.43
    Activations Density 0.000%

    No Known Activations