© 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. 31146
    Prev
    Next
    INDEX
    Explanations

    prices, rates, levels, temps, values changing

    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
     умень
    -0.98
     slowdown
    -0.97
    ícu
    -0.94
     größere
    -0.93
    became
    -0.92
     verstär
    -0.92
    slightly
    -0.90
    lost
    -0.88
    werden
    -0.88
     مات
    -0.88
    POSITIVE LOGITS
     sky
    2.14
     rising
    2.03
     soaring
    1.82
     soared
    1.80
     rise
    1.80
     rises
    1.80
     risen
    1.64
     climb
    1.62
     climbing
    1.59
    rising
    1.58
    Activations Density 0.062%

    No Known Activations