© 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-262K
    7. 1298
    Prev
    Next
    INDEX
    Explanations

    consequences or subsequent events

    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_262k_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
     kemudian
    0.76
    한다
    0.74
     akhirnya
    0.72
     потом
    0.72
     überhaupt
    0.71
    Nowadays
    0.70
    Listo
    0.68
     및
    0.68
     maupun
    0.67
     smile
    0.67
    POSITIVE LOGITS
     years
    1.14
    𝐭
    1.07
     protesters
    1.06
     sebelumnya
    1.04
     failed
    1.04
     disagreements
    0.99
     revelations
    0.99
    𝐤
    0.98
     decades
    0.96
    多年
    0.96
    Activations Density 0.002%

    No Known Activations