© 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-262K
    7. 41546
    Prev
    Next
    INDEX
    Explanations

    shebang lines for interpreters

    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
    coded
    1.27
    nore
    1.18
    p
    1.17
     هذ
    1.16
    pik
    1.16
    nader
    1.13
    nings
    1.12
     kitt
    1.09
    nog
    1.07
     punctu
    1.07
    POSITIVE LOGITS
    駛
    1.20
    ism
    1.13
    ureux
    1.09
    Testables
    1.09
    ist
    1.08
    的情况
    1.07
    的问题
    1.07
    MessageNow
    1.07
     বদি
    1.07
    ーション
    1.05
    Activations Density 0.007%

    No Known Activations