© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117746
    Prev
    Next
    INDEX
    Explanations

    php code and dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Còn
    -0.85
    uture
    -0.83
     zengin
    -0.77
     kuhusu
    -0.74
     deshalb
    -0.73
     Gan
    -0.73
     Bany
    -0.71
    ᚺ
    -0.71
    废话
    -0.71
     Stone
    -0.70
    POSITIVE LOGITS
    使得
    0.86
    酥
    0.82
    析
    0.81
    衲
    0.80
     هستید
    0.79
     royaume
    0.79
    基督
    0.79
     barbe
    0.79
     Nucleus
    0.78
    ทุน
    0.77
    Activations Density 0.000%

    No Known Activations