© 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. 10677
    Prev
    Next
    INDEX
    Explanations

    wartime communism

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

    part shade

    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
    ߋ
    0.32
     اینڈ
    0.31
     бясплатна
    0.30
     içerisinde
    0.29
     אשר
    0.29
     offrant
    0.29
    ♐
    0.29
    🔢
    0.29
    ૈ
    0.29
    漃
    0.29
    POSITIVE LOGITS
     early
    0.38
     murderous
    0.36
     Stalingrad
    0.36
     communist
    0.36
     demarcation
    0.36
     bombing
    0.36
     wartime
    0.35
     Leningrad
    0.35
     violent
    0.35
     oorlog
    0.34
    Activations Density 0.001%

    No Known Activations