© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 73706
    Prev
    Next
    INDEX
    Explanations

    words starting with Is

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

    The neuron activates on standalone, uppercase “IS” tokens (as in acronyms or initialisms).

    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
    Propel
    -0.77
    IMER
    -0.75
    we
    -0.74
     indicado
    -0.74
    からね
    -0.73
    郎
    -0.73
     zonas
    -0.73
     other
    -0.73
     Forder
    -0.72
    なと
    -0.71
    POSITIVE LOGITS
    gangs
    0.88
    soby
    0.87
     Nuestro
    0.87
    yj
    0.84
     ISLAM
    0.84
    énus
    0.82
     salmón
    0.82
     anún
    0.82
    РТ
    0.82
    ſa
    0.82
    Activations Density 0.032%

    No Known Activations