© 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. 22-GEMMASCOPE-RES-131K
    7. 65592
    Prev
    Next
    INDEX
    Explanations

    charting music records

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

    The neuron detects biographical metadata passages—that is, text listing dates, places, nationalities, and occupations (e.g. birth/death dates and roles).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     research
    -1.25
     volverá
    -1.24
     hacemos
    -1.24
     además
    -1.22
     scorso
    -1.21
    𓂂
    -1.21
     السياس
    -1.20
    gregor
    -1.20
     currently
    -1.19
     project
    -1.18
    POSITIVE LOGITS
     използ
    1.45
     salade
    1.40
    ledad
    1.40
    辉煌
    1.38
    𝐘
    1.37
    Localisation
    1.33
     oubli
    1.33
     triom
    1.26
     壁纸
    1.25
    
    1.25
    Activations Density 0.155%

    No Known Activations