© 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. 13-GEMMASCOPE-2-RES-16K
    7. 13302
    Prev
    Next
    INDEX
    Explanations

    quiet solitude

    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_13_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
     worse
    0.84
    Updater
    0.81
     physical
    0.75
     connections
    0.74
     poor
    0.74
    ента
    0.73
     compulsory
    0.73
    邯
    0.73
     information
    0.73
     city
    0.73
    POSITIVE LOGITS
     exclusiva
    1.55
     privacidade
    1.55
     solitude
    1.52
     privacidad
    1.52
     Exclusive
    1.48
     exclusivo
    1.41
     exclusivos
    1.40
     privacy
    1.35
     seclusion
    1.34
    privacy
    1.33
    Activations Density 0.201%

    No Known Activations