© 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
    3. Gemma-3-1B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 3626
    Prev
    Next
    INDEX
    Explanations

    abstract and concrete concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-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
     s
    0.74
    わけで
    0.68
     called
    0.67
     long
    0.66
     "...
    0.66
     Tip
    0.65
     plan
    0.64
     gar
    0.64
    र्श
    0.63
     করল
    0.62
    POSITIVE LOGITS
     crystallinity
    0.91
    閡
    0.84
     diversidad
    0.83
     ontological
    0.82
     dichotom
    0.82
    diversity
    0.82
     materiality
    0.81
     kosakata
    0.80
    fontsize
    0.80
     getHeight
    0.80
    Activations Density 0.126%

    No Known Activations