© 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. 10220
    Prev
    Next
    INDEX
    Explanations

    used after believe or be

    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
    ный
    1.26
    ي
    1.23
    ных
    1.17
    ين
    1.14
    ры
    1.13
    メートル
    1.13
    пи
    1.04
     системы
    1.04
    上がり
    1.04
     будет
    1.02
    POSITIVE LOGITS
    o
    1.21
    c
    1.05
    n
    0.98
    vät
    0.95
     Others
    0.95
     profusely
    0.92
    và
    0.91
    struck
    0.90
    ज
    0.89
    Others
    0.89
    Activations Density 0.000%

    No Known Activations