© 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. 84666
    Prev
    Next
    INDEX
    Explanations

    This invention or question

    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
     我们
    -2.70
    嫘
    -2.19
     但是
    -2.17
    陕
    -2.17
     beslu
    -2.09
    หรือ
    -2.09
    fiddle
    -2.05
    芗
    -2.05
    芨
    -2.03
     voelen
    -2.00
    POSITIVE LOGITS
    s
    3.48
    2
    2.91
    "
    2.41
    4
    2.28
    {
    2.25
    h
    2.13
    3
    2.08
    苤
    2.02
     innymi
    2.02
    ized
    2.02
    Activations Density 0.000%

    No Known Activations