© 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. 31-GEMMASCOPE-2-RES-16K
    7. 15699
    Prev
    Next
    INDEX
    Explanations

    don't followed by a verb

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

    do not rely on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_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
    爹
    0.48
    Hallo
    0.47
     correctement
    0.47
    Bonjour
    0.45
    밖에
    0.45
     cautionary
    0.45
    ിയി
    0.45
    Можно
    0.44
    الله
    0.44
    ᐈ
    0.44
    POSITIVE LOGITS
     underestimate
    0.63
     confuse
    0.54
    expect
    0.52
     miscon
    0.52
     दीजिएगा
    0.51
     অমন
    0.49
     expect
    0.47
    uvos
    0.47
     कीजिएगा
    0.47
     jangan
    0.46
    Activations Density 0.217%

    No Known Activations