© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72034
    Prev
    Next
    INDEX
    Explanations

    Cloud Foundry, Holly Holly

    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
    蟥
    -3.44
     häufigsten
    -3.09
    </i>
    -2.80
    臜
    -2.78
     haupts
    -2.69
     groter
    -2.67
    艽
    -2.63
    ′,
    -2.61
    
    -2.58
     verschied
    -2.55
    POSITIVE LOGITS
     '
    3.08
    ]
    2.52
     -
    2.44
    ing
    2.33
     chrétienne
    2.31
     .....
    2.31
    ISIONS
    2.27
                    
    2.27
    目的是
    2.23
    家が
    2.19
    Activations Density 0.006%

    No Known Activations