© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48111
    Prev
    Next
    INDEX
    Explanations

    lists of items or code snippets

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

    The neuron is specialized to pick up numeric reference markers—numbers embedded in or adjacent to sequences of punctuation (e.g. footnote/citation indices with dots).

    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
    meia
    -0.84
    のではないでしょうか
    -0.81
    えっ
    -0.81
    iddharth
    -0.76
    ATES
    -0.75
    न्ह
    -0.75
     товар
    -0.75
    Around
    -0.75
    视着
    -0.74
    vestream
    -0.73
    POSITIVE LOGITS
     Defin
    0.90
    REDIS
    0.89
    Ранее
    0.82
    櫚
    0.82
     glycos
    0.82
    ∨
    0.81
    APPE
    0.81
     trench
    0.77
     reman
    0.77
    lack
    0.77
    Activations Density 0.011%

    No Known Activations