© 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. 234326
    Prev
    Next
    INDEX
    Explanations

    introduces members, system, prayers, climb

    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
     darse
    0.53
     ceb
    0.50
     Crimes
    0.50
     detention
    0.50
     dada
    0.50
     q
    0.49
     PowerPoint
    0.48
     Fabrication
    0.47
     Prayers
    0.47
     Nº
    0.46
    POSITIVE LOGITS
    Atual
    0.55
    パ
    0.51
    диа
    0.48
    মে
    0.47
    メ
    0.45
    ключение
    0.45
    ジュ
    0.45
    આ
    0.45
     публи
    0.44
    أ
    0.44
    Activations Density 0.000%

    No Known Activations