© 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. 34-GEMMASCOPE-RES-131K
    7. 83955
    Prev
    Next
    INDEX
    Explanations

    block

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

    The neuron strongly activates on standalone numeric tokens (numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    zungs
    -0.82
    ksana
    -0.81
     baka
    -0.81
     datter
    -0.77
     حسب
    -0.76
     Invitation
    -0.76
    ordinated
    -0.75
    saying
    -0.74
     amarela
    -0.74
    posicion
    -0.73
    POSITIVE LOGITS
     Block
    1.11
    Block
    1.06
     unblock
    1.02
     BLOCK
    0.96
     block
    0.94
    블
    0.90
     kleineren
    0.84
    BLOCK
    0.84
     Blok
    0.82
     bloc
    0.81
    Activations Density 0.042%

    No Known Activations