© 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. 15206
    Prev
    Next
    INDEX
    Explanations

    opening files or defining contexts

    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
    ity
    0.92
    If
    0.92
    I
    0.90
    Bs
    0.88
    us
    0.87
    IS
    0.87
    Is
    0.86
    if
    0.85
    ia
    0.85
    ya
    0.84
    POSITIVE LOGITS
     defensor
    0.93
    으로써
    0.88
     unborn
    0.88
     kanyang
    0.86
     nascent
    0.85
     amministrat
    0.85
     seinem
    0.84
    withProperties
    0.83
    嶄
    0.83
     pilot
    0.82
    Activations Density 0.125%

    No Known Activations