© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 16272
    Prev
    Next
    INDEX
    Explanations

    exercise, cooking, and 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
     alphabetical
    1.25
    ස
    1.24
     boldly
    1.23
     Parking
    1.17
     chartered
    1.14
    ది
    1.13
     tangente
    1.12
     Ventilation
    1.12
     DBA
    1.10
     Phylogenetic
    1.10
    POSITIVE LOGITS
    de
    1.50
    ר
    1.40
    ட்ட
    1.21
    t
    1.13
    tos
    1.13
    tir
    1.12
     düş
    1.08
    twe
    1.07
    Cuál
    1.02
    cu
    1.01
    Activations Density 0.018%

    No Known Activations