© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 4843
    Prev
    Next
    INDEX
    Explanations

    Mal- prefix

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

    malware and malicious intent

    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_53_width_65k_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
    هن
    0.42
    ාර
    0.41
     রহমানকে
    0.40
    ডো
    0.40
    রণ
    0.40
    
    0.40
     موب
    0.39
    大力
    0.39
    ນິກ
    0.39
    TintMode
    0.38
    POSITIVE LOGITS
    efic
    0.59
    volent
    0.56
    branche
    0.50
     mal
    0.49
    heureusement
    0.49
    ignant
    0.48
    veillance
    0.47
    씀
    0.47
     Mal
    0.47
    achite
    0.47
    Activations Density 0.035%

    No Known Activations