© 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. 34-GEMMASCOPE-RES-131K
    7. 32030
    Prev
    Next
    INDEX
    Explanations

    selling, cash, valuation

    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
    affordable
    -0.96
     inexpensive
    -0.95
     affordable
    -0.94
    cheap
    -0.94
    Cost
    -0.87
     Cost
    -0.86
     Affordable
    -0.85
     supplies
    -0.83
    Affordable
    -0.83
     Kosten
    -0.82
    POSITIVE LOGITS
     cash
    1.26
     valuations
    1.16
     valuation
    1.14
     Sell
    1.13
    cash
    1.09
    valuation
    1.09
    Cash
    1.07
     evaluations
    1.06
    Sell
    1.05
     appraisal
    1.05
    Activations Density 0.015%

    No Known Activations