© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32263
    Prev
    Next
    INDEX
    Explanations

    presenting/pushing view controllers

    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
     Norwalk
    -0.75
    ฝ
    -0.71
    /***
    -0.69
    waża
    -0.67
    think
    -0.66
    adoc
    -0.66
    등학교
    -0.65
    krebs
    -0.65
    Figure
    -0.64
     Tig
    -0.64
    POSITIVE LOGITS
     蕾
    0.75
    桝
    0.69
    𝐮
    0.69
     invasión
    0.68
    )−
    0.68
    itsch
    0.67
     TOL
    0.66
    🧖
    0.65
    jící
    0.65
    想知道
    0.63
    Activations Density 0.056%

    No Known Activations