© 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. 241293
    Prev
    Next
    INDEX
    Explanations

    foreign words and concepts

    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
    ninja
    0.56
     heist
    0.53
     rumoured
    0.49
     thief
    0.48
     γ
    0.47
     dominates
    0.47
     optimizations
    0.46
    𝓁
    0.46
     murderer
    0.45
     verkaufen
    0.45
    POSITIVE LOGITS
    どの
    0.55
    促进
    0.50
     உத
    0.48
    疥
    0.48
    oxygène
    0.47
    膵
    0.47
    কর্ম
    0.46
     geeign
    0.45
     নিমিত
    0.45
    治疗
    0.44
    Activations Density 0.000%

    No Known Activations