© 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. 90107
    Prev
    Next
    INDEX
    Explanations

    Titles starting with followed word

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

    The neuron selectively activates on capitalized name‐ or title‐tokens (proper nouns and other named‐entity words).

    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
     satisfactor
    -1.09
     compatri
    -1.05
    অ
    -1.02
     Synag
    -0.96
     morena
    -0.95
    很是
    -0.94
    jewództ
    -0.93
     nô
    -0.93
     Polynesia
    -0.92
     prestig
    -0.91
    POSITIVE LOGITS
     system
    1.37
    therlands
    1.23
     method
    1.09
    niest
    1.05
     öppna
    1.05
    ropractor
    1.02
     family
    1.00
     compagnia
    0.97
     userDao
    0.97
     affitto
    0.96
    Activations Density 0.281%

    No Known Activations