© 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. 34-GEMMASCOPE-RES-131K
    7. 48567
    Prev
    Next
    INDEX
    Explanations

    numbers followed by zero

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

    The neuron is specialized to pick out standalone numeric tokens (digits) in the text.

    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
     again
    -1.02
    ftone
    -0.98
    lijke
    -0.90
    今度は
    -0.85
    ímetros
    -0.85
    варя
    -0.85
    minute
    -0.84
    ctose
    -0.84
    :"+
    -0.84
    óricos
    -0.82
    POSITIVE LOGITS
    0
    1.22
     ähnlich
    1.00
    <0x80>
    0.95
     regelmäßig
    0.92
     mehrm
    0.85
    cellence
    0.84
     similar
    0.82
     like
    0.82
    čnega
    0.82
    Mga
    0.81
    Activations Density 0.014%

    No Known Activations