© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66535
    Prev
    Next
    INDEX
    Explanations

    oftentimes

    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
    </b>
    -2.09
    配备
    -1.84
     그는
    -1.74
    驀
    -1.69
    稱為
    -1.69
    慚
    -1.69
    ด้าน
    -1.66
    politician
    -1.65
    \
    -1.64
    丝毫
    -1.63
    POSITIVE LOGITS
    </h3>
    2.44
    there
    2.06
    ست
    2.03
    沨
    2.03
    ſu
    1.95
     Its
    1.91
     glaubte
    1.83
    ات
    1.81
    ();
    1.80
     wußte
    1.80
    Activations Density 0.002%

    No Known Activations