© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68460
    Prev
    Next
    INDEX
    Explanations

    qualification criteria

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

    This neuron fires on occurrences of the term “eligibility” (including headings and mentions of eligibility).

    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
     –
    -2.28
     должна
    -2.13
     vair
    -2.13
    啣
    -2.09
    Perhaps
    -2.02
    あります
    -2.00
     міста
    -1.99
    出て
    -1.94
    f
    -1.93
     their
    -1.91
    POSITIVE LOGITS
    蕻
    2.44
     mentes
    2.13
     wob
    2.11
     gracios
    2.09
    }$.
    2.09
     estric
    2.06
     invitaciones
    2.05
    ⬯
    2.05
    都想
    2.05
     respostas
    2.02
    Activations Density 0.002%

    No Known Activations