© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47654
    Prev
    Next
    INDEX
    Explanations

    OH followed by various endings

    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
     TCA
    -0.79
     Quantities
    -0.73
    Unfortunately
    -0.72
     新聞
    -0.72
    Several
    -0.72
     Morph
    -0.71
    𖥻
    -0.71
    そこで
    -0.71
     balcon
    -0.71
    atguigu
    -0.69
    POSITIVE LOGITS
     dear
    1.01
     OH
    0.97
    ared
    0.85
     yeah
    0.83
    anthem
    0.82
     overhead
    0.81
    SqlClient
    0.81
    嘲
    0.78
     Ohio
    0.76
    unable
    0.76
    Activations Density 0.029%

    No Known Activations