© 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. 137473
    Prev
    Next
    INDEX
    Explanations

    ransomware and decryption

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

    ransomware

    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
     خل
    0.44
    Violation
    0.43
    场所
    0.41
    忽视
    0.40
     السنة
    0.40
     அல
    0.39
     breakage
    0.39
    🚶
    0.39
     காங்கிரஸ்
    0.38
     Break
    0.38
    POSITIVE LOGITS
     ransomware
    0.72
     ransom
    0.63
    ransom
    0.54
     Ransom
    0.50
     hostage
    0.46
     తా
    0.46
     decrypt
    0.46
     payment
    0.46
     hostages
    0.45
     Economía
    0.45
    Activations Density 0.049%

    No Known Activations