© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118124
    Prev
    Next
    INDEX
    Explanations

    at affordable prices

    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
    bodied
    -0.89
    clad
    -0.84
    tening
    -0.82
    다
    -0.79
    patho
    -0.79
    mong
    -0.78
     HAVING
    -0.78
    othermic
    -0.78
    NESS
    -0.77
    üedad
    -0.77
    POSITIVE LOGITS
     reasonable
    3.33
     affordable
    2.89
    reasonable
    2.66
    Reasonable
    2.45
     Reasonable
    2.39
    合理
    2.05
     prices
    2.00
    affordable
    1.92
     fair
    1.88
    Affordable
    1.69
    Activations Density 0.031%

    No Known Activations