© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 48371
    Prev
    Next
    INDEX
    Explanations

    war, assault, nuclear

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    써
    0.79
    ंबू
    0.76
    وە
    0.71
    s
    0.64
    Ḍ
    0.64
    濩
    0.64
    schutz
    0.63
     사
    0.62
    pessoa
    0.62
    ژ
    0.61
    POSITIVE LOGITS
    ı
    0.93
    ;
    0.84
    ne
    0.75
    í
    0.72
     aumentando
    0.68
    ة
    0.68
    يد
    0.67
    ing
    0.66
    만큼
    0.66
    ínt
    0.66
    Activations Density 0.002%

    No Known Activations