© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10144
    Prev
    Next
    INDEX
    Explanations

    one treatment

    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
    s
    -5.44
    4
    -3.73
    >
    -3.61
    的
    -3.59
    3
    -3.56
    ve
    -3.52
    5
    -3.44
    b
    -3.39
    r
    -3.39
    by
    -3.36
    POSITIVE LOGITS
    玏
    3.89
    醅
    3.42
    ឵
    3.25
    浤
    3.22
    嫆
    3.20
    ſſen
    3.05
    塤
    3.02
    ญี่ป
    2.97
     univerz
    2.91
    któ
    2.88
    Activations Density 0.026%

    No Known Activations