© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130099
    Prev
    Next
    INDEX
    Explanations

    The neuron responds to technical psychoanalytic terminology.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    psychoanalysis and unconscious concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    っこう
    -1.43
     réserver
    -1.40
    ּוֹ
    -1.39
     consommer
    -1.34
    ostante
    -1.33
     oogen
    -1.32
     appeler
    -1.31
    ૉ
    -1.31
    last
    -1.30
     décider
    -1.30
    POSITIVE LOGITS
     Dichtung
    1.39
    ฉัน
    1.30
     clás
    1.30
     primeras
    1.30
     first
    1.27
     or
    1.27
     decorativos
    1.23
    četně
    1.23
    obedience
    1.21
     cristianismo
    1.20
    Activations Density 0.061%

    No Known Activations