© 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. 238067
    Prev
    Next
    INDEX
    Explanations

    Monk, Atlas, Ella, Texas, Paris

    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
     깊
    0.61
     اقدام
    0.56
     المسافه
    0.55
    ༔
    0.55
     먼저
    0.54
     کوم
    0.54
     그래프
    0.53
     고객
    0.53
     코
    0.53
     حمایت
    0.53
    POSITIVE LOGITS
     Monk
    0.46
     Pool
    0.45
    </h2>
    0.44
     Atlas
    0.44
     Ella
    0.44
     Texas
    0.43
    ції
    0.43
     Rou
    0.42
    </h3>
    0.42
     Paris
    0.42
    Activations Density 0.000%

    No Known Activations