© 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. 17-GEMMASCOPE-2-RES-16K
    7. 1854
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_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
    ities
    1.05
    <eos>
    0.88
    []
    0.83
    us
    0.83
    answer
    0.81
    ative
    0.81
    com
    0.79
     继续访问
    0.76
    or
    0.75
    е
    0.75
    POSITIVE LOGITS
     empêcher
    1.19
     bảo
    1.15
    ইল
    1.13
     Maintains
    1.13
     Öncelikle
    1.12
     übertr
    1.09
     impide
    1.09
     schützen
    1.08
     extrêmement
    1.07
     Absence
    1.06
    Activations Density 0.795%

    No Known Activations