© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110824
    Prev
    Next
    INDEX
    Explanations

    verb "go" with direction/purpose

    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
    があった
    -0.91
     Brüder
    -0.90
     afirmou
    -0.87
     izquierdo
    -0.86
    在这里
    -0.86
    lunda
    -0.86
     Königin
    -0.84
    ()))
    
    -0.84
    æng
    -0.82
     megsz
    -0.82
    POSITIVE LOGITS
     to
    1.52
     into
    1.21
     out
    0.98
     with
    0.91
     along
    0.88
     after
    0.81
    towej
    0.75
     armed
    0.75
     before
    0.73
     about
    0.73
    Activations Density 0.026%

    No Known Activations