© 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. 90621
    Prev
    Next
    INDEX
    Explanations

    words starting with W

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

    The neuron is strongly activated by uppercase abbreviation fragments (acronyms/initialisms and their punctuation).

    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
    Dazu
    -0.85
    Natürlich
    -0.84
    Genau
    -0.83
    Leider
    -0.81
    Außerdem
    -0.77
     occult
    -0.77
    Beratung
    -0.76
    Spenden
    -0.75
     એ
    -0.74
    Herzliche
    -0.74
    POSITIVE LOGITS
    wireless
    1.27
    Wireless
    1.25
     Weighted
    1.18
     Wireless
    1.13
    Wedding
    1.12
    Weighted
    1.12
    Water
    1.11
    white
    1.11
     Welfare
    1.10
    wavelength
    1.10
    Activations Density 0.080%

    No Known Activations