© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10384
    Prev
    Next
    INDEX
    Explanations

    negative emotions and difficult circumstances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     INTEGR
    2.03
    ிலான
    2.01
    TECHN
    2.00
    يفي
    1.96
    oucí
    1.91
    촤
    1.88
     맞춰
    1.86
     갖
    1.86
     તૈયાર
    1.85
     മിക
    1.83
    POSITIVE LOGITS
     severity
    2.39
     scourge
    2.32
     perpetrated
    2.30
     illness
    2.25
     oppression
    2.19
     incur
    2.12
     inflicted
    2.07
     diss
    2.07
    袭击
    2.06
     illnesses
    2.06
    Activations Density 0.351%

    No Known Activations