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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 3901
    Prev
    Next
    INDEX
    Explanations

    code best practices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-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
    eureka
    0.86
    omers
    0.81
    ǎi
    0.81
    ₎
    0.80
     DIFFERENT
    0.80
     doings
    0.79
    PlatformTarget
    0.79
    λλά
    0.78
     denominators
    0.78
    crops
    0.78
    POSITIVE LOGITS
     ultra
    0.95
     paranoid
    0.92
     paranoia
    0.90
    氓
    0.88
     Prevent
    0.86
     anti
    0.85
     protect
    0.84
     security
    0.83
     Escape
    0.83
     Ultra
    0.82
    Activations Density 0.098%

    No Known Activations