© 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. 77268
    Prev
    Next
    INDEX
    Explanations

    p tags and the letter p

    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
     lembaga
    -0.93
    نگار
    -0.82
    pie
    -0.81
     SEDS
    -0.81
    𝜋
    -0.78
     marginLeft
    -0.76
    pull
    -0.74
    opan
    -0.74
    žno
    -0.73
    Post
    -0.73
    POSITIVE LOGITS
     p
    4.91
    p
    3.59
     P
    2.06
    ｐ
    2.06
     getP
    1.96
    𝑝
    1.96
    setP
    1.84
    getP
    1.77
    P
    1.69
     pp
    1.60
    Activations Density 0.058%

    No Known Activations