© 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. 127173
    Prev
    Next
    INDEX
    Explanations

    military operations and control

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

    explanation for a change

    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
     unsuccessfully
    0.47
    നാണ്
    0.46
     arouse
    0.46
     கிடைத்தது
    0.46
    нули
    0.45
     ។
    0.44
    𝟕
    0.44
    を迎
    0.44
    قم
    0.43
    ப்பட்டன
    0.43
    POSITIVE LOGITS
     ANON
    0.40
    built
    0.39
     silo
    0.39
    balance
    0.38
    banking
    0.38
     dlatego
    0.38
    balanced
    0.38
     मंत्रिमंडल
    0.38
    زالة
    0.37
    control
    0.37
    Activations Density 0.000%

    No Known Activations