© 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. 78764
    Prev
    Next
    INDEX
    Explanations

    ap, apl, Op, AP

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on BPE subword pieces beginning with the letter sequence “ap.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     dy
    -0.88
    <bos>
    -0.86
     claro
    -0.79
    日が
    -0.75
     Schro
    -0.75
    lena
    -0.74
     dice
    -0.74
    を
    -0.73
    rece
    -0.72
    这些
    -0.72
    POSITIVE LOGITS
    Comunic
    0.96
     endIndex
    0.84
    葎
    0.83
    zení
    0.82
    AuthGuard
    0.81
    際に
    0.80
    warzys
    0.79
    注释
    0.79
    URAS
    0.79
    んですけど
    0.77
    Activations Density 0.011%

    No Known Activations