© 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. 43676
    Prev
    Next
    INDEX
    Explanations

    following Service, conditions

    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
    {
    -3.77
    后
    -2.89
    卝
    -2.56
     The
    -2.39
    蠖
    -2.28
    -2.23
    的
    -2.19
    都有
    -2.19
    y
    -2.17
    ebenarnya
    -2.16
    POSITIVE LOGITS
    酲
    3.22
    獃
    2.83
    </em>
    2.66
    玧
    2.58
    艄
    2.52
    ญี่ป
    2.48
     dreaded
    2.44
    〤
    2.39
    磲
    2.36
    猹
    2.30
    Activations Density 0.052%

    No Known Activations