© 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. 34-GEMMASCOPE-RES-131K
    7. 93583
    Prev
    Next
    INDEX
    Explanations

    XML namespaces

    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
     including
    -0.98
    including
    -0.88
    包括
    -0.86
    )\}$
    -0.85
     dostępne
    -0.85
     incluyendo
    -0.82
    Sinopse
    -0.82
    valbard
    -0.82
     tendría
    -0.77
    thanks
    -0.77
    POSITIVE LOGITS
    蕪
    0.94
             
    0.84
     class
    0.82
    上前
    0.81
     id
    0.80
    !***
    0.80
                  
    0.79
              
    0.78
     Beech
    0.77
    PYTHON
    0.77
    Activations Density 0.009%

    No Known Activations