© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 14845
    Prev
    Next
    INDEX
    Explanations

    examples of concepts

    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
     eluted
    1.48
    ف
    1.30
     aaye
    1.26
     Agora
    1.26
    the
    1.22
     firmas
    1.22
     diagonals
    1.20
     células
    1.19
    Eleven
    1.18
     seems
    1.17
    POSITIVE LOGITS
    ی
    1.27
    itarian
    1.16
    rological
    1.14
     whopping
    1.11
    RuntimeException
    1.11
     multifaceted
    1.10
     disposizione
    1.09
     deterrent
    1.09
     makeshift
    1.08
     topographic
    1.08
    Activations Density 0.113%

    No Known Activations