© 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. 12-GEMMASCOPE-2-RES-16K
    7. 7135
    Prev
    Next
    INDEX
    Explanations

    . followed by method names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    ে
    1.57
    ி
    1.41
    了
    1.38
    iunea
    1.37
    
    1.30
    鵡
    1.30
     assailant
    1.29
     travailler
    1.26
     двумя
    1.24
    Ү
    1.23
    POSITIVE LOGITS
    on
    2.05
    in
    2.03
    at
    1.76
    ä
    1.76
    ě
    1.70
    od
    1.62
    ó
    1.60
    if
    1.52
    to
    1.52
    ulated
    1.49
    Activations Density 0.041%

    No Known Activations