© 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. 22-GEMMASCOPE-RES-131K
    4. 68114
    Prev
    Next
    INDEX
    Explanations

    array indexing and size

    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_22/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
     samb
    -0.75
     auprès
    -0.75
    🌅
    -0.74
     brevis
    -0.73
    -.-
    -0.71
     schrij
    -0.71
    WSER
    -0.71
     clark
    -0.71
    numberOf
    -0.70
    tigungs
    -0.70
    POSITIVE LOGITS
     jouant
    0.90
    一方
    0.88
     sortant
    0.85
    측
    0.84
     whereas
    0.82
    sinki
    0.82
     특
    0.82
    侧
    0.81
     เช
    0.79
     víctimas
    0.78
    Activations Density 0.227%

    No Known Activations