© 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-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-262K
    7. 3704
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_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
    На
    1.28
    За
    1.24
    Но
    1.20
    Во
    1.16
    い
    1.15
    Все
    1.14
    Вы
    1.13
    По
    1.12
    И
    1.11
    ا
    1.10
    POSITIVE LOGITS
    kę
    0.96
     gyr
    0.93
     harnesses
    0.93
    artment
    0.93
     automation
    0.93
     teething
    0.88
     doubly
    0.87
     redundancies
    0.86
    τής
    0.84
     samoglas
    0.84
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.