© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 28064
    Prev
    Next
    INDEX
    Explanations

    exclamation marks

    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
    ’
    -3.13
     is
    -2.66
     $
    -2.08
    -
    -1.97
     -
    -1.96
     do
    -1.95
     as
    -1.90
     by
    -1.88
    圏
    -1.80
    
    -1.79
    POSITIVE LOGITS
     作り方
    2.31
    ⎊
    2.22
    嗶
    2.13
    before
    2.11
    ishment
    2.09
    ፲
    2.06
    孓
    2.03
    ㎉
    2.02
    未だ
    2.02
    PARATOR
    2.02
    Activations Density 0.007%

    No Known Activations