© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74468
    Prev
    Next
    INDEX
    Explanations

    back in the day

    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
    fetchone
    -1.57
    おすすめの
    -1.55
     mnoho
    -1.55
    urably
    -1.52
     vorige
    -1.50
    ⅅ
    -1.49
    )$.
    -1.46
     několik
    -1.43
     thirteen
    -1.41
    ⃢
    -1.40
    POSITIVE LOGITS
    ”
    1.85
     
    1.79
    ことが
    1.60
     возможность
    1.58
     \
    1.56
    \
    1.55
     таких
    1.54
     Herausforderung
    1.52
     новый
    1.49
     именно
    1.45
    Activations Density 0.001%

    No Known Activations