© 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. 100910
    Prev
    Next
    INDEX
    Explanations

    tours and activities

    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
    𝄆
    -2.78
    鋱
    -2.53
    ？）
    -2.39
    ！）
    -2.30
    或者
    -2.30
    艄
    -2.25
    麽
    -2.23
    岽
    -2.19
     \&
    -2.17
    ？』
    -2.16
    POSITIVE LOGITS
    h
    2.64
    la
    2.59
     These
    2.55
    鹚
    2.53
    (
    2.47
     Their
    2.44
    Ⅳ
    2.39
    u
    2.38
     Frühling
    2.27
     Them
    2.25
    Activations Density 0.007%

    No Known Activations