© 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. 45520
    Prev
    Next
    INDEX
    Explanations

    circular buffer indices and states

    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
    ками
    -0.85
     чолові
    -0.82
     být
    -0.80
    直到
    -0.77
    chläge
    -0.75
     surfacing
    -0.75
     כדי
    -0.74
     byť
    -0.73
    rscheinlich
    -0.73
    блица
    -0.73
    POSITIVE LOGITS
     filled
    1.08
     next
    1.07
     currentIndex
    1.02
     occupied
    1.00
     current
    0.99
    tail
    0.99
    currentIndex
    0.98
    filled
    0.96
     запол
    0.94
    occupied
    0.94
    Activations Density 0.011%

    No Known Activations