© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 166315
    Prev
    Next
    INDEX
    Explanations

    "demilitarize" or "demilitarizing" and conquest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    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
     funeral
    0.50
     sleeping
    0.48
     Verk
    0.46
    殓
    0.45
    funeral
    0.43
     Sleeping
    0.43
     sleepers
    0.43
     viewing
    0.42
     funerals
    0.42
     sleeper
    0.41
    POSITIVE LOGITS
     eaten
    0.36
    蛛
    0.36
     أعلام
    0.35
    يرة
    0.35
     termasuk
    0.35
     תש
    0.35
    차
    0.35
    琊
    0.35
     বোঝ
    0.35
     точек
    0.35
    Activations Density 0.001%

    No Known Activations