© 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. 95399
    Prev
    Next
    INDEX
    Explanations

    code and math notation anchors

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

    The neuron activates on numeric tokens (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
    eff
    -0.79
     انه
    -0.79
     Installed
    -0.77
    Installing
    -0.74
     ΤΟ
    -0.71
     Betrach
    -0.70
    To
    -0.69
    規劃
    -0.69
     July
    -0.69
    攞
    -0.69
    POSITIVE LOGITS
    acción
    1.04
    geddon
    0.93
     dieną
    0.92
     tấm
    0.88
     manier
    0.88
    राब
    0.85
     phosph
    0.84
    inar
    0.84
    Teks
    0.83
    IBIL
    0.82
    Activations Density 0.025%

    No Known Activations