© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57758
    Prev
    Next
    INDEX
    Explanations

    adult followed by topic

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

    The neuron fires strongly on the word “adult,” i.e. it detects occurrences of “Adult” (or “adult”) in the text.

    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
     représentation
    -1.03
     grève
    -0.99
    りゃ
    -0.98
     diversité
    -0.96
    vantaged
    -0.93
     detalhes
    -0.91
     poursuite
    -0.88
     sensibilité
    -0.87
     greateſt
    -0.85
     totalité
    -0.85
    POSITIVE LOGITS
     adult
    2.06
    Adult
    1.98
     Adult
    1.88
    adult
    1.60
     Adults
    1.40
     adults
    1.38
     ADULT
    1.34
     beverage
    1.24
     adulto
    1.23
    onema
    1.23
    Activations Density 0.030%

    No Known Activations