© 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. 41-GEMMASCOPE-2-RES-65K
    7. 14225
    Prev
    Next
    INDEX
    Explanations

    say "Russian adjective endings"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
    喜び
    0.54
    岃
    0.52
     Net
    0.51
    etically
    0.50
    épid
    0.50
     ஏற்ற
    0.49
    кого
    0.49
    堝
    0.48
     Nb
    0.48
    技能
    0.48
    POSITIVE LOGITS
    ное
    2.16
    ny
    2.14
    ная
    2.09
    ные
    2.08
    ный
    2.06
    ný
    2.06
    nych
    2.05
    ных
    2.03
    ной
    2.02
    ным
    2.02
    Activations Density 0.016%

    No Known Activations