© 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. 10-GEMMASCOPE-RES-131K
    7. 128764
    Prev
    Next
    INDEX
    Explanations

    second items

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

    The neuron activates on occurrences of the ordinal “second.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    荩
    -1.88
    geſ
    -1.77
    世间
    -1.67
     Tento
    -1.55
    乆
    -1.54
    iſter
    -1.52
    .
    -1.50
    livro
    -1.43
    <td>
    -1.41
    鬟
    -1.41
    POSITIVE LOGITS
    玧
    1.98
    谵
    1.88
    獃
    1.70
    m
    1.70
    a
    1.67
    鲼
    1.66
    蠓
    1.63
    second
    1.59
    ₁)
    1.53
    t
    1.52
    Activations Density 0.055%

    No Known Activations