© 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-16K
    7. 5688
    Prev
    Next
    INDEX
    Explanations

    video series, exception rule, gangster rap

    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_24_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
    ،
    0.77
     JobList
    0.76
    Bart
    0.75
     संय
    0.74
    𝕋
    0.72
    Mil
    0.71
    ，
    0.69
    Birthday
    0.68
    Ϝ
    0.68
    ℍ
    0.68
    POSITIVE LOGITS
    ure
    0.93
     heme
    0.88
     będą
    0.81
    गें
    0.80
    ä
    0.80
     veer
    0.79
    दर्शिता
    0.79
    ้
    0.79
    ेक्स
    0.77
    et
    0.77
    Activations Density 0.001%

    No Known Activations