© 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. 98245
    Prev
    Next
    INDEX
    Explanations

    additional information

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

    The neuron strongly activates on occurrences of the word “additional” (including its component substrings).

    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
    ником
    -0.94
    diator
    -0.91
    Proceed
    -0.89
    dila
    -0.89
    ög
    -0.89
    IMES
    -0.85
    Tongue
    -0.84
     itulah
    -0.84
    образие
    -0.84
    ➗
    -0.84
    POSITIVE LOGITS
    tional
    1.72
    tionally
    1.46
    Info
    1.27
    nal
    1.16
    Information
    1.08
     to
    1.07
     Info
    1.02
    cional
    1.02
    info
    0.99
    INFO
    0.99
    Activations Density 0.031%

    No Known Activations