© 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. 10-GEMMASCOPE-RES-131K
    7. 102222
    Prev
    Next
    INDEX
    Explanations

    jack

    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_10/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
    it
    -2.23
    <em>
    -2.13
    <u>
    -2.11
     But
    -2.09
    *
    -2.08
    </strong>
    -2.06
    –
    -2.03
    n
    -2.02
    v
    -1.98
     $-$
    -1.97
    POSITIVE LOGITS
     帅气
    2.25
    唿
    2.06
    ‌ها
    2.03
     kjer
    1.91
     Langkah
    1.88
    BIÉN
    1.87
     生命周期
    1.84
    genodigd
    1.83
     tabloid
    1.82
     इसलिए
    1.81
    Activations Density 0.013%

    No Known Activations