© 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
    2. Gemma-3-12B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 14811
    Prev
    Next
    INDEX
    Explanations

    values, equations, or trainable layers

    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_31_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
     سوف
    0.66
     meningkatkan
    0.59
     Zuh
    0.59
    }+(
    0.55
     aumentare
    0.55
     Niveau
    0.54
     hins
    0.54
     Zil
    0.52
    ")}
    0.52
    จึง
    0.51
    POSITIVE LOGITS
    oges
    0.60
    ходим
    0.59
    ந்த்
    0.58
    ходе
    0.58
    values
    0.57
    equality
    0.56
     study
    0.55
    Values
    0.55
     values
    0.54
    anter
    0.54
    Activations Density 0.000%

    No Known Activations