© 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. 612
    Prev
    Next
    INDEX
    Explanations

    abstract qualities

    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
    ن
    2.80
    ع
    2.18
     ambulance
    2.18
    おそらく
    2.14
    نن
    2.13
    ש
    2.10
    бору
    2.07
    雱
    2.06
    お
    2.02
    主义
    2.01
    POSITIVE LOGITS
    sure
    2.18
    days
    2.07
    VA
    2.04
    sli
    1.99
    trong
    1.98
    𝑒
    1.98
     Нача
    1.95
    untamiento
    1.93
    tart
    1.93
     Tatiana
    1.91
    Activations Density 1.219%

    No Known Activations