© 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. 9344
    Prev
    Next
    INDEX
    Explanations

    rubber wheel tire inspection

    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
    定律
    1.29
    愪
    1.27
     수행
    1.25
    କ୍
    1.23
    のように
    1.22
     ダウン
    1.22
    で
    1.22
    ରେ
    1.21
     armario
    1.20
     जाकर
    1.15
    POSITIVE LOGITS
    n
    1.27
    an
    1.20
    ar
    1.20
    en
    1.16
    н
    1.16
    ao
    1.13
    real
    1.13
    ς
    1.12
    o
    1.11
    ul
    1.10
    Activations Density 0.099%

    No Known Activations