© 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. 3872
    Prev
    Next
    INDEX
    Explanations

    navigating diverse perspectives

    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
    1.70
     don
    1.24
     didn
    1.12
     doesn
    1.11
     isn
    1.09
     and
    1.05
     wasn
    1.02
     only
    1.02
    .
    1.01
    ↵↵
    1.00
    POSITIVE LOGITS
    向け
    1.17
    AVOA
    1.16
    ukiyoe
    1.16
    Storia
    1.09
     தமிழரசுக்
    1.06
    向けの
    1.05
    occasione
    1.03
    Ciao
    1.02
    Allora
    1.02
    侑
    1.02
    Activations Density 0.825%

    No Known Activations