© 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-3-12B
    5. 12-GEMMASCOPE-2-RES-16K
    7. 292
    Prev
    Next
    INDEX
    Explanations

    interview questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_12_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
    s
    0.98
    ใน
    0.77
     Rund
    0.77
    aan
    0.76
    ف
    0.76
    ς
    0.75
     Opfer
    0.75
    aus
    0.74
     daleko
    0.74
    藥
    0.73
    POSITIVE LOGITS
    їз
    0.97
    raving
    0.96
     elapse
    0.92
     mockup
    0.91
     turnkey
    0.84
     catalyze
    0.83
     frugal
    0.82
     nonthermal
    0.82
     mydb
    0.81
     baffling
    0.81
    Activations Density 0.000%

    No Known Activations