© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 47658
    Prev
    Next
    INDEX
    Explanations

    javascript function definitions or calls

    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_34/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
     arşivlendi
    -1.29
     parfüm
    -1.28
     sokak
    -1.27
    (!__
    -1.22
     bús
    -1.18
    ={()
    -1.14
     sánh
    -1.14
    锨
    -1.10
     (!__
    -1.09
     fön
    -1.05
    POSITIVE LOGITS
     (
    2.77
    (
    1.95
     on
    1.09
    }(
    1.07
    </em>
    0.94
     during
    0.94
    +");
    0.93
    </strong>
    0.90
    }")
    
    0.90
    <em>
    0.90
    Activations Density 0.011%

    No Known Activations