© 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. 10-GEMMASCOPE-RES-131K
    7. 90788
    Prev
    Next
    INDEX
    Explanations

    affluent chandeliers or evidently

    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
    ↵
    -2.73
    y
    -2.72
     $_=
    -2.47
    ズニー
    -2.22
    replyreport
    -2.19
     باسلام
    -2.16
     puede
    -2.13
    ⽥
    -2.11
     cũng
    -2.09
    癀
    -2.09
    POSITIVE LOGITS
     
    3.09
     '
    3.05
    }
    3.03
    \
    2.98
    {
    2.95
     $\
    2.41
    ]
    2.27
    几分
    2.22
    \\
    2.19
    ERS
    2.17
    Activations Density 0.001%

    No Known Activations