© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3486
    Prev
    Next
    INDEX
    Explanations

    terrorist organizations and attacks

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

    potential for harmful information misuse

    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
     आविष्कार
    0.50
     చక్ర
    0.49
     শাস্ত্র
    0.48
    🥃
    0.47
     அதிசயம்
    0.47
    Ꮀ
    0.46
    ⏯
    0.46
     Discharge
    0.45
     ჭ
    0.45
     Manager
    0.45
    POSITIVE LOGITS
     terrorist
    3.23
     terrorists
    3.16
     terrorism
    2.86
     आतंकवादी
    2.75
     терро
    2.75
     आतंकी
    2.66
    terror
    2.48
    terrorism
    2.47
     Terrorism
    2.47
    Terror
    2.44
    Activations Density 0.160%

    No Known Activations