© 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. 275
    Prev
    Next
    INDEX
    Explanations

    programming and multilingual text

    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
    VISED
    -1.03
     bayan
    -0.94
    ージョン
    -0.94
    ):
    -0.89
    peł
    -0.88
    mbps
    -0.88
     flore
    -0.88
     later
    -0.88
     fjor
    -0.88
     augusti
    -0.85
    POSITIVE LOGITS
     and
    1.16
    ドウ
    0.96
     delicado
    0.87
    为什么
    0.85
     fuera
    0.84
    ляем
    0.84
     및
    0.82
     oraz
    0.82
     dwind
    0.81
    fazer
    0.81
    Activations Density 0.007%

    No Known Activations