© 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. 10-GEMMASCOPE-RES-131K
    7. 7228
    Prev
    Next
    INDEX
    Explanations

    contact with

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

    The neuron specifically activates on occurrences of the word “contact.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    Ꮵ
    -2.20
    蔸
    -2.16
    鹪
    -2.08
     ſy
    -2.06
     krim
    -2.02
    Ꮷ
    -1.95
    隳
    -1.95
    >
    -1.92
     hóspedes
    -1.88
     optik
    -1.86
    POSITIVE LOGITS
     '
    2.20
    </h4>
    2.11
     Herzens
    2.09
    ')
    2.08
     is
    1.95
     inconspicuous
    1.95
    }
    1.95
     contact
    1.88
     feverish
    1.88
    .........
    1.84
    Activations Density 0.012%

    No Known Activations