© 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. 118151
    Prev
    Next
    INDEX
    Explanations

    Missi- words

    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
     схемы
    -0.78
     licha
    -0.78
     進
    -0.78
    timedia
    -0.77
    kapnya
    -0.76
    脸色
    -0.76
     Interests
    -0.75
    UNIS
    -0.75
    しか
    -0.75
     essai
    -0.74
    POSITIVE LOGITS
    噂
    0.94
    ortiment
    0.93
    大方
    0.81
     Campionato
    0.79
     particularly
    0.78
     typically
    0.75
    apunov
    0.74
    okon
    0.73
     probably
    0.72
     falou
    0.72
    Activations Density 0.041%

    No Known Activations