© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102103
    Prev
    Next
    INDEX
    Explanations

    hen weekend dos

    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
    er
    -2.84
    𓋼
    -2.78
    e
    -2.70
    廕
    -2.61
    鬟
    -2.61
    写真の
    -2.53
    猡
    -2.48
    ه
    -2.45
    ࿆
    -2.42
     them
    -2.41
    POSITIVE LOGITS
    2
    3.14
                    
    3.03
    9
    2.80
    隳
    2.77
     they
    2.75
     You
    2.67
    1
    2.52
    ть
    2.50
     Genau
    2.50
     Möglich
    2.47
    Activations Density 0.004%

    No Known Activations