© 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. 69066
    Prev
    Next
    INDEX
    Explanations

    $_ subscripts

    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
    </sup>
    -3.50
    </h4>
    -2.59
    
    -2.34
     übernahm
    -2.33
     caused
    -2.28
    𖥦
    -2.28
    ଞ
    -2.13
    所需的
    -2.09
    mieszkanie
    -2.08
    ⮜
    -2.08
    POSITIVE LOGITS
     ‘
    2.92
    </i>
    2.69
    逦
    2.44
     (‘
    2.25
    一块
    2.09
     sembler
    2.09
     …
    2.08
     персонал
    2.03
     ’
    1.97
     {
    1.96
    Activations Density 0.007%

    No Known Activations