© 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. 59134
    Prev
    Next
    INDEX
    Explanations

    afaik, AFA, Pfa, fa

    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
     contributors
    -0.76
    tokio
    -0.73
    xae
    -0.71
     contributor
    -0.69
     csapat
    -0.68
     fiecare
    -0.68
    回应
    -0.68
    目前的
    -0.66
     zeichnen
    -0.65
    壷
    -0.65
    POSITIVE LOGITS
    💨
    0.96
     fa
    0.88
     речо
    0.85
     fay
    0.84
    fa
    0.84
    fase
    0.83
    ّد
    0.83
    ziom
    0.81
    💗
    0.80
    erne
    0.80
    Activations Density 0.026%

    No Known Activations