© 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. 47609
    Prev
    Next
    INDEX
    Explanations

    Ab followed by a name

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

    The neuron strongly detects the two‐letter character sequence “ab” (in either lowercase or uppercase) within tokens.

    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
    ビス
    -0.77
     independiente
    -0.77
     EARL
    -0.76
     じ
    -0.75
    户外
    -0.74
    ferenz
    -0.73
     genetically
    -0.72
    xrTableCell
    -0.72
    lobby
    -0.71
    fun
    -0.70
    POSITIVE LOGITS
    了吧
    0.83
    ('../../../
    0.81
    Breath
    0.77
    (")");
    0.76
    يدة
    0.76
    ularis
    0.73
    SDC
    0.73
    ურ
    0.72
    这不是
    0.72
     Ab
    0.72
    Activations Density 0.069%

    No Known Activations