© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 2890
    Prev
    Next
    INDEX
    Explanations

    evaluating risks and safety

    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_22_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
     ബി
    0.82
    charset
    0.74
    étel
    0.73
    compressed
    0.72
    lüsse
    0.71
    chnung
    0.71
     मैट्रिक्स
    0.71
    腆
    0.71
    Marketing
    0.71
    ন্দ
    0.70
    POSITIVE LOGITS
     safety
    3.40
     Safety
    3.19
    Safety
    3.10
    safety
    3.03
     안전
    2.94
     SAFETY
    2.82
    安全
    2.80
     dangers
    2.71
    SAFETY
    2.65
     safer
    2.64
    Activations Density 1.019%

    No Known Activations