Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-1B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 2676
    Prev
    Next
    INDEX
    Explanations

    security, password, encryption

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_17_width_16k_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
     protop
    0.98
    播
    0.80
    Arist
    0.79
     surfactant
    0.77
     Aristotle
    0.75
     Rous
    0.75
     telescop
    0.75
     इंड
    0.74
    唢
    0.74
     IAU
    0.73
    POSITIVE LOGITS
     security
    2.01
     Security
    1.92
    Security
    1.86
     password
    1.73
     cryptography
    1.69
    security
    1.68
     encryption
    1.60
    セキュリティ
    1.60
     SECURITY
    1.59
     Password
    1.59
    Activations Density 1.579%

    No Known Activations