© 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-16K
    7. 7148
    Prev
    Next
    INDEX
    Explanations

    Rembrandt, remediation, remapping, remembers

    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
     scont
    1.25
    От
    1.21
    ر
    1.20
    ात
    1.17
    ंजलि
    1.15
     regole
    1.11
     paso
    1.10
     رد
    1.08
     retour
    1.05
     Sancho
    1.05
    POSITIVE LOGITS
    ならない
    1.33
    tım
    1.29
    ❤️❤️
    1.26
    なりません
    1.23
    tiden
    1.17
    ção
    1.16
     ثقاف
    1.15
    taker
    1.12
    mina
    1.11
    %%%%%%%%
    1.10
    Activations Density 0.070%

    No Known Activations