© 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. 222065
    Prev
    Next
    INDEX
    Explanations

    divorce certificate

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

    technical terms and procedures

    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
     biotechnology
    0.45
     কৃষ
    0.43
     インド
    0.42
     nahi
    0.42
     MADE
    0.42
     乾燥
    0.42
     TECHNOLOGY
    0.41
    ᱤ
    0.41
     pursuing
    0.41
     melindungi
    0.40
    POSITIVE LOGITS
    戞
    0.49
    اريخ
    0.49
     गिरफ्त
    0.48
    말로
    0.48
     immaculate
    0.47
     horrific
    0.46
    archiw
    0.46
    履歴
    0.46
    ابية
    0.45
    ாவ
    0.44
    Activations Density 0.001%

    No Known Activations