© 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. 40-GEMMASCOPE-2-RES-262K
    7. 23325
    Prev
    Next
    INDEX
    Explanations

    Russian aggression and control

    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_40_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
    运
    0.47
     स्‍
    0.44
    ন্দের
    0.44
     remarkably
    0.43
     उन्‍होंने
    0.41
    详
    0.41
     महत्वपूर्ण
    0.41
     eBook
    0.41
    Ｅ
    0.41
    初めて
    0.40
    POSITIVE LOGITS
     crimes
    0.66
     blackmail
    0.65
     преступ
    0.63
     anarch
    0.61
     mafia
    0.61
     aggression
    0.60
     agres
    0.59
     gangster
    0.59
     discredit
    0.59
     stupidity
    0.58
    Activations Density 0.011%

    No Known Activations