© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 372
    Prev
    Next
    INDEX
    Explanations

    proper nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_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
     detectable
    0.80
    ɴ
    0.78
    ️
    0.75
    ED
    0.74
    แบบ
    0.72
     طرح
    0.71
    artwork
    0.67
     joystick
    0.67
    ggplot
    0.67
    expensive
    0.67
    POSITIVE LOGITS
     Monastery
    0.69
    {\'
    0.63
    ia
    0.62
    eské
    0.60
    u
    0.59
    íssimo
    0.59
    may
    0.59
     monastery
    0.58
     Estate
    0.57
    ék
    0.57
    Activations Density 0.121%

    No Known Activations