© 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. 34417
    Prev
    Next
    INDEX
    Explanations

    phone numbers

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

    The neuron strongly activates on sequences of digits and numerical patterns (e.g., multi‐digit numbers, phone‐number–style groupings, 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
    
    -1.11
    ってない
    -1.04
    報導
    -1.04
     タ
    -1.01
     łyż
    -0.99
     ユ
    -0.99
     ゴ
    -0.97
    ☦
    -0.97
    ecause
    -0.96
     ガ
    -0.96
    POSITIVE LOGITS
    ellant
    1.20
     фаса
    1.15
     efficaces
    1.14
    巅峰
    1.12
    Припев
    1.11
     Василь
    1.10
    ременно
    1.09
     úteis
    1.09
     voegen
    1.08
     зима
    1.08
    Activations Density 0.003%

    No Known Activations