© 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. 84840
    Prev
    Next
    INDEX
    Explanations

    case studies

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

    disappearing from

    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
     I
    0.59
     Sch
    0.57
     Scul
    0.51
     Daughter
    0.51
     Manohar
    0.50
     Minaj
    0.50
     Fat
    0.49
     Zhu
    0.49
     King
    0.49
     West
    0.48
    POSITIVE LOGITS
    ném
    0.51
     χρόνια
    0.50
    PROJECT
    0.49
    ோர
    0.49
    年
    0.49
    nomin
    0.48
    presa
    0.48
     систем
    0.47
    姓
    0.47
    深刻
    0.47
    Activations Density 0.000%

    No Known Activations