© 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. 111648
    Prev
    Next
    INDEX
    Explanations

    balls and of

    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
    呓
    -3.34
    沩
    -3.23
    ſam
    -3.14
    鼍
    -3.02
    螄
    -3.00
    ﹔
    -2.94
    ୈ
    -2.81
    镭
    -2.69
     onderwerp
    -2.64
    钜
    -2.64
    POSITIVE LOGITS
     
    3.75
    -
    3.28
    2
    3.06
    Possibly
    3.03
    是
    3.02
    Since
    2.91
    With
    2.91
    4
    2.89
    After
    2.86
    5
    2.84
    Activations Density 0.009%

    No Known Activations