© 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. 22-GEMMASCOPE-RES-131K
    7. 54244
    Prev
    Next
    INDEX
    Explanations

    step or method number

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

    The neuron activates on numeric tokens (including integers and decimal 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_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
     their
    -1.04
    Garonne
    -1.03
     to
    -0.97
    ˃
    -0.96
    isteren
    -0.96
     femininas
    -0.95
    $,
    -0.95
    çois
    -0.93
    Przyp
    -0.93
    )$;
    -0.92
    POSITIVE LOGITS
    ak
    1.06
    ↵↵↵
    0.99
     Lastly
    0.96
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.95
    ky
    0.94
    ↵↵↵↵↵↵↵↵↵↵
    0.93
    ↵↵↵↵↵↵↵↵↵↵↵↵
    0.93
    ↵↵↵↵↵↵↵↵↵
    0.93
    ↵↵↵↵↵↵↵↵↵↵↵
    0.91
    ere
    0.91
    Activations Density 0.023%

    No Known Activations