© 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. 41-GEMMASCOPE-2-RES-262K
    7. 25341
    Prev
    Next
    INDEX
    Explanations

    attack, strike, force, combat

    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_all/layer_41_width_262k_l0_big
    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
    halle
    0.48
    ഷ്യ
    0.47
    耆
    0.44
     yıll
    0.43
     яи
    0.43
     ചരി
    0.43
    ខ្ល
    0.42
    èques
    0.42
    欷
    0.42
     વર્ષ
    0.42
    POSITIVE LOGITS
    攻撃
    0.65
     공격
    0.64
     attack
    0.62
    攻击
    0.62
     attacks
    0.59
     instantaneous
    0.58
     attacking
    0.58
     attaques
    0.56
     attaque
    0.55
     ataque
    0.54
    Activations Density 0.004%

    No Known Activations