© 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. 4679
    Prev
    Next
    INDEX
    Explanations

    years or decades

    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
    ר
    0.50
    ি
    0.47
    hunter
    0.46
    :
    0.45
    ر
    0.45
    ées
    0.45
     надо
    0.44
    er
    0.43
    رى
    0.43
    ется
    0.42
    POSITIVE LOGITS
     rumores
    0.44
    א
    0.43
     in
    0.42
    佲
    0.38
    ول
    0.37
    oporosis
    0.37
    💢
    0.36
    af
    0.36
    து
    0.36
    ць
    0.36
    Activations Density 0.035%

    No Known Activations