© 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. 61194
    Prev
    Next
    INDEX
    Explanations

    native Android software

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

    moral obligations and technology

    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
     eigen
    0.54
     ic
    0.50
     result
    0.48
    lak
    0.47
    狽
    0.47
    riminal
    0.46
    larda
    0.46
    eling
    0.45
     결과
    0.45
    lings
    0.45
    POSITIVE LOGITS
    vitamin
    0.47
    ّ
    0.46
     viên
    0.45
    ี่
    0.45
    вав
    0.44
     فروغ
    0.44
    Vitamin
    0.44
    评标
    0.44
    礁
    0.44
     سے
    0.43
    Activations Density 0.000%

    No Known Activations