© 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. 29-GEMMASCOPE-2-RES-16K
    7. 42
    Prev
    Next
    INDEX
    Explanations

    gentle or careful 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_29_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
     ذاتی
    0.80
     발전
    0.77
     spaw
    0.76
     ಮಾರ
    0.75
    スペック
    0.75
    儲
    0.74
    шит
    0.74
    瑣
    0.74
     समृद्ध
    0.74
    成り立つ
    0.74
    POSITIVE LOGITS
     gently
    1.76
     Gently
    1.51
     gentle
    1.41
     pressing
    1.37
     squeezing
    1.35
     lifting
    1.35
     press
    1.33
     holding
    1.31
     lift
    1.30
     tilting
    1.30
    Activations Density 2.210%

    No Known Activations