© 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. 22-GEMMASCOPE-RES-131K
    7. 71433
    Prev
    Next
    INDEX
    Explanations

    initialization of `i`

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

    This neuron detects array‐subscript expressions—i.e. an identifier immediately followed by a “[” for indexing.

    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
     another
    -1.20
     особли
    -1.09
     başka
    -0.98
     partly
    -0.91
     autre
    -0.91
     particularly
    -0.91
     пить
    -0.90
     دیگری
    -0.89
     outros
    -0.88
     various
    -0.88
    POSITIVE LOGITS
    asier
    1.01
     صفحات
    0.91
    ähle
    0.89
    DECLARE
    0.84
     žal
    0.81
    verbs
    0.81
    óloga
    0.81
    警方
    0.80
    taler
    0.80
    daughters
    0.80
    Activations Density 0.004%

    No Known Activations