© 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. 31149
    Prev
    Next
    INDEX
    Explanations

    two or second

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

    the presence of numeric tokens (especially multi-digit numbers) in the text.

    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
    第一次
    -0.98
     WWI
    -0.98
    ToOne
    -0.94
    xlabel
    -0.93
    一
    -0.92
    Donnell
    -0.92
    好み
    -0.86
     one
    -0.85
    jeune
    -0.85
    第一
    -0.84
    POSITIVE LOGITS
     second
    1.32
     two
    1.20
     deuxième
    1.15
    two
    1.14
     kedua
    1.09
     tweede
    1.02
     drugiej
    1.02
     zweiten
    1.00
     två
    0.98
     dwóch
    0.98
    Activations Density 0.265%

    No Known Activations