© 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. 40750
    Prev
    Next
    INDEX
    Explanations

    winter

    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
    氿
    -2.39
    genodigd
    -2.33
    魮
    -2.28
    lgari
    -2.28
    ᥀
    -2.25
    饪
    -2.22
    珰
    -2.22
    葑
    -2.20
    隳
    -2.19
    勦
    -2.17
    POSITIVE LOGITS
    It
    3.19
     In
    2.77
     With
    2.63
    3
    2.55
    ve
    2.45
    i
    2.41
    </i>
    2.41
    time
    2.39
    w
    2.31
     winter
    2.30
    Activations Density 0.012%

    No Known Activations