© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 11126
    Prev
    Next
    INDEX
    Explanations

    nn modules and functional

    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_24_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
     چاہتا
    0.95
     extinguishers
    0.91
    ığım
    0.88
    ቝ
    0.87
     সালের
    0.86
     기술
    0.84
    했지만
    0.84
     časti
    0.84
     कहती
    0.83
    ᅡ
    0.82
    POSITIVE LOGITS
    i
    0.96
    if
    0.89
    <0x0D>
    0.86
    n
    0.85
    k
    0.81
    es
    0.77
    for
    0.73
    l
    0.73
    in
    0.73
    t
    0.73
    Activations Density 0.000%

    No Known Activations