© 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. 110847
    Prev
    Next
    INDEX
    Explanations

    go [extent/direction]

    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
     going
    -1.06
     Aufmerksamkeit
    -1.01
     ongoing
    -0.94
     gå
    -0.91
     vindo
    -0.86
     rval
    -0.85
     attesa
    -0.83
     lanzar
    -0.83
     thrown
    -0.82
     opportunity
    -0.82
    POSITIVE LOGITS
     overboard
    0.94
     ballistic
    0.91
     سرا
    0.90
     notches
    0.85
    uatu
    0.85
     unnoticed
    0.85
    tecs
    0.84
    犊
    0.83
    hrung
    0.83
     lengths
    0.82
    Activations Density 0.042%

    No Known Activations