© 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. 10-GEMMASCOPE-RES-131K
    7. 127236
    Prev
    Next
    INDEX
    Explanations

    common prefixes and suffixes

    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_10/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
     to
    -2.31
     or
    -1.91
    ↵↵
    -1.78
     pierws
    -1.65
     alebo
    -1.50
     detalladas
    -1.43
     not
    -1.43
     seguirá
    -1.39
     contrase
    -1.39
     in
    -1.38
    POSITIVE LOGITS
    1.82
    .
    1.77
     they
    1.73
    するという
    1.65
    .

    1.58
    <td>
    1.58
    liest
    1.57
    ═
    1.55
    quíni
    1.49
    																				
    1.49
    Activations Density 0.025%
    No Known Activations