© 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. 64725
    Prev
    Next
    INDEX
    Explanations

    first

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

    The neuron is a general “background” detector that fires most strongly on very common or high‐frequency words (especially short function words like “at” and “out” and other frequent tokens).

    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
     Zelanda
    -0.95
     multiuso
    -0.93
     چهارم
    -0.92
     currentIndex
    -0.91
    żył
    -0.90
    ᴹ
    -0.90
    Second
    -0.90
    никами
    -0.87
    火影
    -0.87
    Cuándo
    -0.87
    POSITIVE LOGITS
     first
    10.06
    first
    6.34
     primero
    5.78
     ersten
    5.69
     primeiro
    5.63
     první
    5.59
     eerste
    5.25
     πρώ
    4.97
     primeira
    4.94
     eerst
    4.94
    Activations Density 0.630%

    No Known Activations