© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 2717
    Prev
    Next
    INDEX
    Explanations

    attackers and enemies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_65k_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
    bble
    0.63
     decouple
    0.63
    ‚¬
    0.63
    Receipt
    0.62
    忏
    0.61
     decou
    0.61
    回収
    0.61
    犧
    0.61
    énération
    0.61
     Transactions
    0.60
    POSITIVE LOGITS
     enemy
    2.73
     enemies
    2.65
     adversaries
    2.53
     invaders
    2.36
     attackers
    2.35
    enemy
    2.34
     foes
    2.33
     adversary
    2.32
     villains
    2.31
    敌人
    2.28
    Activations Density 0.435%

    No Known Activations