© 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. 22-GEMMASCOPE-RES-131K
    7. 16305
    Prev
    Next
    INDEX
    Explanations

    URLs, brand names, and topics

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

    The neuron fires on the very first token of a new section or block (e.g. the initial “http” in a link line or the first word of the following paragraph).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     privada
    -1.01
     senaste
    -0.98
     configurações
    -0.96
    ofed
    -0.96
    karena
    -0.96
    usive
    -0.94
     évé
    -0.94
     largura
    -0.91
    tentu
    -0.91
     защото
    -0.91
    POSITIVE LOGITS
    appliquent
    1.11
     anunció
    1.06
     ответить
    1.05
     habló
    1.01
    Okay
    0.97
    院校
    0.96
    OK
    0.93
    tituts
    0.92
    ipts
    0.90
    ăsp
    0.90
    Activations Density 0.000%

    No Known Activations