© 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. 22-GEMMASCOPE-RES-131K
    7. 66893
    Prev
    Next
    INDEX
    Explanations

    going to be

    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_22/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
     sometimes
    -1.32
    してしまった
    -1.19
    ⾃
    -1.16
     when
    -1.13
     moż
    -1.10
     Sometimes
    -1.09
     recently
    -1.09
    詼
    -1.09
     other
    -1.06
     often
    -1.06
    POSITIVE LOGITS
     will
    1.40
     be
    1.29
    我们
    1.28
     будет
    1.24
    (!__
    1.23
     (!__
    1.17
    至少
    1.14
    setCellStyle
    1.14
    我們
    1.13
    Beaucoup
    1.13
    Activations Density 0.023%

    No Known Activations