© 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. 118010
    Prev
    Next
    INDEX
    Explanations

    makes a difference

    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
    rieden
    -0.95
     redacción
    -0.91
    estimating
    -0.87
    ıyı
    -0.86
    kerja
    -0.86
    📵
    -0.85
    ってみました
    -0.82
    μένου
    -0.81
    
    -0.80
     entretenimiento
    -0.80
    POSITIVE LOGITS
     make
    4.00
     makes
    3.89
     making
    2.94
    make
    2.67
     Makes
    2.63
    Make
    2.61
     made
    2.53
    Makes
    2.45
     Make
    2.44
    makes
    2.30
    Activations Density 0.025%

    No Known Activations