© 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. 53119
    Prev
    Next
    INDEX
    Explanations

    medical abbreviations and punctuation

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

    crises and death

    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
     命令
    0.52
     三角
    0.51
    掘
    0.50
     生成
    0.48
    ссу
    0.47
     不能
    0.47
    odi
    0.46
    incer
    0.46
    emakers
    0.46
    商
    0.44
    POSITIVE LOGITS
     effets
    0.49
    நர்
    0.46
     дов
    0.46
     inim
    0.44
     Lass
    0.43
     Effekt
    0.43
    ματα
    0.43
    ματος
    0.43
     terrib
    0.42
    Ⲙ
    0.42
    Activations Density 0.000%

    No Known Activations