© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 5758
    Prev
    Next
    INDEX
    Explanations

    Notre Dame Cathedral

    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_16k_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
     fluctuate
    1.09
     Vér
    1.02
    あります
    1.02
     อย่า
    1.00
     Passwort
    0.99
    Ќ
    0.99
    Przyp
    0.99
     furiously
    0.98
     Zusätzlich
    0.97
    Ví
    0.96
    POSITIVE LOGITS
    v
    1.35
    op
    1.27
    é
    1.23
    t
    1.23
    iz
    1.19
    id
    1.15
    p
    1.14
    st
    1.13
    m
    1.10
    ä
    1.10
    Activations Density 0.001%

    No Known Activations