© 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. 22-GEMMASCOPE-2-RES-65K
    7. 6026
    Prev
    Next
    INDEX
    Explanations

    tr followed by icks, icked, or ilers

    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_65k_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
     truth
    1.00
     twin
    0.95
    ܒ
    0.93
    دا
    0.88
    яв
    0.88
    ೃಹ
    0.86
    twin
    0.86
     truly
    0.84
    ك
    0.80
     צריך
    0.80
    POSITIVE LOGITS
    jillo
    1.17
    iscuit
    1.14
    NSDictionary
    1.11
    와이스
    1.11
    あえず
    1.08
     आर्मी
    1.02
     показыва
    1.00
     phú
    1.00
     equil
    0.99
     td
    0.99
    Activations Density 0.433%

    No Known Activations