© 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. 39190
    Prev
    Next
    INDEX
    Explanations

    mimicking or imitated

    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
    ╿
    -3.53
    嗵
    -2.95
     یا
    -2.88
    ፝
    -2.86
    镞
    -2.86
    她
    -2.86
     发型
    -2.86
     torba
    -2.80
    我们
    -2.77
     adoration
    -2.77
    POSITIVE LOGITS
    2
    4.19
    ing
    3.66
    h
    3.53
    which
    3.38
    v
    3.38
    ar
    3.28
    .
    3.23
     be
    3.11
    A
    3.08
    ––
    3.03
    Activations Density 0.005%

    No Known Activations