© 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
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11376
    Prev
    Next
    INDEX
    Explanations

    instead or rather

    np_acts-logits-general · gemini-2.5-flash-lite

    contrast and substitution

    np_acts-logits-general · gemini-2.5-flash-lite

    instead

    np_max-act-logits · claude-4-5-sonnetTriggered by @sripadkarne
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StringTo
    0.32
     antaranya
    0.32
    ্বাস
    0.32
    <0xEB>
    0.32
    ровка
    0.32
     மண்ட
    0.32
    থি
    0.31
    ান্ড
    0.30
     ||
    0.30
     Range
    0.30
    POSITIVE LOGITS
     instead
    3.86
    instead
    3.70
     rather
    3.56
    而不是
    3.52
     вместо
    3.45
    rather
    3.36
    而非
    3.22
    Instead
    3.20
     plutôt
    3.17
     Instead
    3.09
    Activations Density 1.107%

    No Known Activations