© 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-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 5789
    Prev
    Next
    INDEX
    Explanations

    privacy, VPN, or service names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    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
    ኸ
    1.02
     surroundings
    0.97
     MCD
    0.97
     Dant
    0.96
    นด์
    0.95
     lymphocytes
    0.94
     Kf
    0.93
     vector
    0.93
    loginfo
    0.93
    которы
    0.89
    POSITIVE LOGITS
    3
    1.04
     følgende
    1.00
    $
    0.95
    \
    0.93
    <b>
    0.93
    {
    0.93
    2
    0.91
    9
    0.91
    {$\
    0.88
    .
    0.88
    Activations Density 0.289%

    No Known Activations