© 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-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 203156
    Prev
    Next
    INDEX
    Explanations

    insist / insistence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_37_width_262k_l0_small_affine
    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
    veriş
    0.44
    wab
    0.43
    axos
    0.40
     тем
    0.37
     Ге
    0.36
    itext
    0.36
    ErrorClazz
    0.36
    }}(\
    0.35
     VB
    0.35
     TRADE
    0.35
    POSITIVE LOGITS
     insist
    1.85
     insisted
    1.70
     insisting
    1.70
     insistence
    1.67
     insists
    1.60
     insistent
    1.33
    堅持
    1.29
     stubbornly
    1.23
    坚持
    1.19
     stubborn
    1.08
    Activations Density 0.150%

    No Known Activations