© 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. 190135
    Prev
    Next
    INDEX
    Explanations

    his daughter

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

    photographer style, hotel tier

    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
     ฉาก
    0.51
    ]\\
    0.49
    \\
    0.47
     Mutual
    0.46
     Wunder
    0.46
    xture
    0.46
    ,​
    0.46
     Radiation
    0.45
     rainwater
    0.45
     Nucl
    0.45
    POSITIVE LOGITS
    وش
    0.49
     کیوں
    0.46
    おお
    0.44
    밖
    0.44
     داش
    0.43
    チャレンジ
    0.43
    meet
    0.43
    وشی
    0.43
     দেবযানীর
    0.43
     commemorate
    0.42
    Activations Density 0.001%

    No Known Activations