© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14475
    Prev
    Next
    INDEX
    Explanations

    Peter Rost

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

    The neuron primarily activates on numeric tokens (i.e. sequences of digits).

    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
     februari
    -0.88
     thân
    -0.81
     pattes
    -0.79
    畸
    -0.74
     réf
    -0.74
    🏈
    -0.73
    頸
    -0.73
    >-
    -0.73
     -
    -0.72
     рит
    -0.72
    POSITIVE LOGITS
     Consejos
    1.01
    
    0.98
     Insol
    0.97
    Галерея
    0.96
     jednego
    0.94
     распростра
    0.93
    τεί
    0.93
    𝗐
    0.92
    ៩
    0.90
     badkamer
    0.89
    Activations Density 0.001%

    No Known Activations