© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 83727
    Prev
    Next
    INDEX
    Explanations

    Chowk, Chaat, Chach, Chehertha, Chauhan, Chawla, Chalana, Chiranjeevi

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

    The neuron strongly activates on any token that begins with the letters “Ch,” i.e. it detects the “Ch-” character sequence at the start of 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_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
    none
    -0.85
     synthe
    -0.82
     elev
    -0.82
    醍
    -0.81
    اہ
    -0.79
    edy
    -0.79
    时的
    -0.78
    更何况
    -0.78
     conta
    -0.77
    still
    -0.76
    POSITIVE LOGITS
    itário
    0.91
    為に
    0.88
     goederen
    0.86
     whirl
    0.85
    تمبر
    0.84
     whirling
    0.84
    öss
    0.83
     prodigy
    0.82
    țial
    0.81
    minipage
    0.81
    Activations Density 0.008%

    No Known Activations