© 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. 194085
    Prev
    Next
    INDEX
    Explanations

    describing objects or states

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

    poem reflecting admiration

    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
    主人公
    0.49
    بيه
    0.48
    Prest
    0.47
    prüfung
    0.47
    بسم
    0.46
    लिस
    0.46
    广
    0.45
    卖
    0.45
    小组
    0.44
    اکی
    0.44
    POSITIVE LOGITS
     Jeremy
    0.47
     لح
    0.46
     nig
    0.46
     Peter
    0.46
     種
    0.45
     di
    0.44
     ん
    0.44
     veden
    0.44
     Richard
    0.44
     depression
    0.44
    Activations Density 0.002%

    No Known Activations