© 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. 17-GEMMASCOPE-2-RES-16K
    7. 8151
    Prev
    Next
    INDEX
    Explanations

    Fissure, Swarm, Determinism

    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_17_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
    us
    1.24
    dylib
    1.04
     mikä
    1.00
    س
    1.00
    arod
    0.99
    ní
    0.97
    க
    0.96
    らい
    0.95
    어야
    0.93
    sı
    0.92
    POSITIVE LOGITS
     desvi
    1.38
     hashes
    1.28
     shields
    1.24
     locks
    1.22
     angrily
    1.22
     siendo
    1.21
    벵
    1.20
    尙
    1.20
     hurriedly
    1.19
     teniendo
    1.19
    Activations Density 0.007%

    No Known Activations