© 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. 28040
    Prev
    Next
    INDEX
    Explanations

    compute for my

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

    The neuron is specialized to pick up numeric tokens—standalone digits or numbers (including multi‐digit figures and numeric expressions).

    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
    dekor
    -1.18
     konkrete
    -1.12
    baju
    -1.09
    bánh
    -1.09
    atique
    -1.09
     echte
    -1.03
     Aufenthal
    -1.02
    saat
    -1.02
     pulsera
    -1.02
    matician
    -1.01
    POSITIVE LOGITS
     first
    1.70
     since
    1.42
    首先
    1.27
     here
    1.27
     Since
    1.23
    first
    1.20
     evidently
    1.19
     by
    1.18
     using
    1.17
     firstly
    1.17
    Activations Density 0.065%

    No Known Activations