© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9127
    Prev
    Next
    INDEX
    Explanations

    accidents and injuries

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

    crime and danger

    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_40_width_16k_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
    derdag
    0.47
     ভবিষ্যতের
    0.43
     WhatsApp
    0.41
     ஆர்வ
    0.41
     হোয়াটসঅ্যাপ
    0.41
    ūs
    0.40
    jols
    0.40
    ◝
    0.38
    agés
    0.38
    weak
    0.37
    POSITIVE LOGITS
     kidnapping
    1.41
     accident
    1.35
     kidnapped
    1.35
     দুর্ঘট
    1.34
     accidents
    1.32
     kidnap
    1.30
    accident
    1.23
     burglary
    1.22
     kidn
    1.20
    事故
    1.20
    Activations Density 0.561%

    No Known Activations