© 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. 38622
    Prev
    Next
    INDEX
    Explanations

    concepts of separation

    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
    यर
    -0.81
     Wiggins
    -0.75
    իլ
    -0.73
     kolek
    -0.72
    وزش
    -0.72
     AttributeSet
    -0.71
    dents
    -0.69
    ρίς
    -0.68
    ͕
    -0.67
    urile
    -0.66
    POSITIVE LOGITS
     separation
    6.53
     separated
    5.97
     separating
    5.72
     Separation
    5.44
     separates
    5.44
    separation
    5.25
    Separation
    5.13
     Separ
    5.13
     separate
    5.06
    separated
    5.03
    Activations Density 0.243%

    No Known Activations