© 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. 94625
    Prev
    Next
    INDEX
    Explanations

    explosives bombs ordnance fireworks

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

    bombs, explosives, detonation, harm

    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
    强势
    0.46
     menuMobile
    0.44
     krwi
    0.44
     σύ
    0.43
     hız
    0.43
    鬓
    0.43
     وهم
    0.43
    स्थापित
    0.42
    PersonalInfo
    0.41
     Urlaub
    0.41
    POSITIVE LOGITS
     explosives
    1.36
     detonation
    1.34
     deton
    1.30
     bombs
    1.20
     detonations
    1.20
    炸
    1.18
     explosive
    1.17
     explosions
    1.16
    爆炸
    1.14
     Explos
    1.09
    Activations Density 0.104%

    No Known Activations