© 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. 54294
    Prev
    Next
    INDEX
    Explanations

    foreign characters and numbers

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

    The neuron strongly fires on content‐bearing tokens—especially nouns, identifiers, units, or numbers (e.g. material names, variable names, numeric values).

    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
     nela
    -1.04
     FÜR
    -0.93
    ୈ
    -0.91
     Ży
    -0.89
    Apparently
    -0.87
    Something
    -0.85
     lonely
    -0.84
     rodas
    -0.82
     przyzna
    -0.82
    Clearly
    -0.81
    POSITIVE LOGITS
    –
    1.11
    נוּ
    1.00
     dieną
    0.89
    īgs
    0.88
    であり
    0.87
    ccedil
    0.86
     during
    0.86
     mensen
    0.86
    Açık
    0.86
     Akufo
    0.85
    Activations Density 0.035%

    No Known Activations