© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 84454
    Prev
    Next
    INDEX
    Explanations

    mathematical and programming symbols"""

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

    The neuron primarily fires on numeric tokens—i.e. digits or numeric literals in code or math.

    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
     ubica
    -1.46
     ilyen
    -1.12
     kompati
    -1.10
     cordón
    -1.05
     peliculas
    -1.03
     kokona
    -1.02
    感は
    -1.02
     schuldig
    -1.02
    ∛
    -1.01
     geringe
    -1.00
    POSITIVE LOGITS
     отсутствие
    0.96
    رائه
    0.93
     financière
    0.93
     expor
    0.91
     arra
    0.90
    勻
    0.88
    引言
    0.87
    el
    0.86
     エ
    0.85
     sowohl
    0.84
    Activations Density 0.007%

    No Known Activations