© 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. 10-GEMMASCOPE-RES-131K
    7. 68188
    Prev
    Next
    INDEX
    Explanations

    words with 'ig'

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

    This neuron responds to the character sequence “ig,” activating whenever that bigram appears in a token.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    नलोड
    -2.78
    ༷
    -2.72
     mereka
    -2.56
    龊
    -2.52
    “
    -2.50
    箆
    -2.47
     slew
    -2.44
    狁
    -2.42
    鋮
    -2.41
    ࿚
    -2.39
    POSITIVE LOGITS
    ig
    3.98
    }$
    3.09
    的
    3.05
    k
    2.78
    est
    2.72
    ay
    2.72
    ol
    2.58
    re
    2.52
    et
    2.50
    歘
    2.36
    Activations Density 0.010%

    No Known Activations