© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 191823
    Prev
    Next
    INDEX
    Explanations

    Japanese sentiments escalation

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

    characteristics and features

    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
    Not in Any Lists

    No Comments

    Negative Logits
     ASU
    0.46
     hauled
    0.42
     hauling
    0.41
    必ず
    0.40
     UGA
    0.39
     haul
    0.39
    不知
    0.39
    ぜ
    0.39
     véritable
    0.39
     termine
    0.39
    POSITIVE LOGITS
     కొత్త
    0.52
     crebre
    0.52
     గే
    0.50
     인기
    0.49
     ప్రీ
    0.48
    Allister
    0.47
    erder
    0.47
    Tools
    0.47
    en
    0.47
     నా
    0.47
    Activations Density 0.001%

    No Known Activations