© 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. 49163
    Prev
    Next
    INDEX
    Explanations

    oh and similar interjections

    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
    otá
    -0.94
     despite
    -0.91
     this
    -0.81
    Bingo
    -0.81
     if
    -0.76
    佻
    -0.74
     similarly
    -0.74
    歹
    -0.74
     sacerd
    -0.73
     what
    -0.73
    POSITIVE LOGITS
     oh
    6.09
    Oh
    5.88
     Oh
    5.81
    oh
    4.59
     OH
    3.61
    哦
    3.59
    OH
    3.28
    ohs
    2.23
     Ohio
    2.03
     ohms
    2.02
    Activations Density 0.039%

    No Known Activations