© 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
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 2830
    Prev
    Next
    INDEX
    Explanations

    causing or motivating action

    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
    u
    2.55
    ીએ
    2.46
    
    2.32
    ^{
    2.29
    tender
    2.28
    os
    2.22
     travelling
    2.19
     incapac
    2.12
     devised
    2.11
     Peut
    2.08
    POSITIVE LOGITS
    서
    2.64
    в
    2.55
    که
    2.29
    เคลื่อน
    2.25
    grimas
    2.24
     arrayOf
    2.23
    надцать
    2.22
    uerung
    2.17
    findElement
    2.14
     withd
    2.10
    Activations Density 0.313%

    No Known Activations