© 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. 49802
    Prev
    Next
    INDEX
    Explanations

    multiple fronts

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

    The neuron activates on standalone numeric tokens (e.g. years, counts, or other 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
    __)
    -0.79
    Viitteet
    -0.79
     panahon
    -0.75
     Consideration
    -0.74
    nó
    -0.73
    ThemeOverlay
    -0.73
    ystemen
    -0.73
    ży
    -0.73
     Stru
    -0.73
     valueForKey
    -0.71
    POSITIVE LOGITS
     fronts
    3.80
     front
    2.95
    front
    2.63
     Front
    2.03
    Front
    2.02
    fron
    1.98
     FRONT
    1.87
    FRONT
    1.84
     counts
    1.77
     фрон
    1.70
    Activations Density 0.020%

    No Known Activations