© 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. 12112
    Prev
    Next
    INDEX
    Explanations

    instantiate view controller

    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
    י
    -0.79
    arm
    -0.74
    ༄
    -0.67
    leq
    -0.66
    setDefault
    -0.66
     משפ
    -0.65
     család
    -0.65
    neq
    -0.65
     GG
    -0.64
    ust
    -0.63
    POSITIVE LOGITS
     Automó
    0.73
    ྲ
    0.71
    pread
    0.71
    towym
    0.70
     DISPOSAL
    0.70
    اصله
    0.69
    alugar
    0.68
    Adres
    0.68
    ствовать
    0.67
     jugó
    0.66
    Activations Density 0.072%

    No Known Activations