© 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. 89121
    Prev
    Next
    INDEX
    Explanations

    years , open close

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

    html tag

    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
    تقه
    0.48
    مرة
    0.46
    甠
    0.45
    خرى
    0.45
     kirj
    0.44
     pago
    0.44
     pembangunan
    0.43
     사무
    0.43
    неоп
    0.43
     möj
    0.43
    POSITIVE LOGITS
    cA
    0.49
    Pics
    0.48
    ეც
    0.47
    cF
    0.47
     ছি
    0.45
     ='
    0.45
     بيت
    0.45
    cD
    0.44
    ImageIcon
    0.44
    Syl
    0.44
    Activations Density 0.000%

    No Known Activations