© 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. 8447
    Prev
    Next
    INDEX
    Explanations

    describing immediate actions

    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_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
    ,
    1.26
    gers
    1.04
    ，
    1.02
    e
    1.00
    ى
    0.97
    ος
    0.96
    ：
    0.94
    ぇ
    0.93
    .$,
    0.91
    、
    0.91
    POSITIVE LOGITS
     anticipating
    1.38
     encountering
    1.35
     submitting
    1.27
     constituting
    1.26
     obtaining
    1.24
     completing
    1.23
     embodying
    1.22
     adhering
    1.19
     accessing
    1.19
     recognizing
    1.19
    Activations Density 0.037%

    No Known Activations