© 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. 22-GEMMASCOPE-RES-131K
    7. 72375
    Prev
    Next
    INDEX
    Explanations

    punctuations and numbers

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

    The neuron activates whenever it sees a numeric token (digits or numbers, including integers and decimals).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     usati
    -0.99
    😕
    -0.95
    ];
    -0.88
    </b>
    -0.88
    \},
    -0.87
     usare
    -0.86
     selezion
    -0.86
    ]'
    -0.86
    💇
    -0.85
     أن
    -0.85
    POSITIVE LOGITS
     Unglück
    1.09
     dalších
    1.05
     Saltar
    1.03
    Гео
    1.01
     čtyř
    0.99
    england
    0.98
     tampoco
    0.97
     while
    0.95
     ditto
    0.94
     móg
    0.94
    Activations Density 0.050%

    No Known Activations