© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 87198
    Prev
    Next
    INDEX
    Explanations

    legal documents and official contexts

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

    Okay, answers about subjectivity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     fondament
    0.44
     Perfecto
    0.43
     Chimie
    0.43
    사와
    0.43
     Fiscalía
    0.42
     spruce
    0.41
     Ressourcen
    0.40
     ય
    0.40
     conscientious
    0.40
     Consciousness
    0.40
    POSITIVE LOGITS
     njega
    0.47
     цього
    0.45
     aikana
    0.44
    這
    0.44
    摑
    0.43
    繃
    0.43
    worth
    0.42
    impin
    0.42
    ifo
    0.42
     нього
    0.42
    Activations Density 0.000%

    No Known Activations