© 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. 4199
    Prev
    Next
    INDEX
    Explanations

    connect execute React

    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
    Familie
    -0.77
    interess
    -0.76
    Elke
    -0.75
     correndo
    -0.75
     Fridays
    -0.74
     stopp
    -0.73
    āti
    -0.72
     olmak
    -0.72
     zacht
    -0.72
    Ingen
    -0.71
    POSITIVE LOGITS
    ⱼ
    0.80
    vieran
    0.79
     alarmed
    0.79
    컨
    0.79
    但是
    0.76
    DataOutputStream
    0.76
    巫
    0.76
    りん
    0.76
    ということで
    0.74
    嬤
    0.73
    Activations Density 0.039%

    No Known Activations