© 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. 87150
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming

    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
    diğim
    -0.79
     Kindern
    -0.78
    onPressed
    -0.77
    companying
    -0.77
    дан
    -0.77
    specular
    -0.77
    gencias
    -0.75
    ystemet
    -0.75
     judges
    -0.74
    ESTRE
    -0.74
    POSITIVE LOGITS
    setLayout
    0.96
    Theres
    0.82
     arranged
    0.81
    Grip
    0.78
     Sentiment
    0.76
    arranged
    0.75
    tivitas
    0.75
    代わりに
    0.74
     perma
    0.74
     achtergrond
    0.74
    Activations Density 0.005%

    No Known Activations