© 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. 34-GEMMASCOPE-RES-131K
    7. 76625
    Prev
    Next
    INDEX
    Explanations

    public license

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

    The neuron primarily activates on standalone numeric tokens (individual digits or small multi‐digit 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
    ghijklmnop
    -0.84
    سف
    -0.79
    有序
    -0.78
    těte
    -0.78
    Entrevista
    -0.77
    ἆ
    -0.77
    ticiones
    -0.77
    afari
    -0.76
     Suga
    -0.76
     infek
    -0.75
    POSITIVE LOGITS
     мили
    0.77
     membri
    0.75
     détail
    0.73
    dika
    0.73
     Others
    0.72
     сре
    0.71
    🦶
    0.70
     Jacksonville
    0.69
     Zé
    0.69
    men
    0.66
    Activations Density 0.006%

    No Known Activations