© 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. 78630
    Prev
    Next
    INDEX
    Explanations

    tech company names and domains

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

    The neuron fires on tokens that are segments of web addresses (e.g. domain names and URL parts).

    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
     while
    -1.18
     and
    -1.04
     with
    -1.03
     PEM
    -0.93
     on
    -0.92
     Kritik
    -0.91
     at
    -0.90
    로운
    -0.90
     would
    -0.89
     samb
    -0.89
    POSITIVE LOGITS
     keo
    1.12
     zajíma
    1.08
     sugerencias
    1.05
     REPUBLIC
    1.03
     corrientes
    1.02
     novamente
    1.02
     sicht
    1.00
     barvy
    0.96
     preocupaciones
    0.96
     magnifiques
    0.96
    Activations Density 0.054%

    No Known Activations