© 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. 5220
    Prev
    Next
    INDEX
    Explanations

    own X

    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
    क
    2.09
    č
    2.09
    dür
    1.98
    ร์
    1.77
    ce
    1.71
    ೆ
    1.62
    ि
    1.57
    çe
    1.55
     inorder
    1.53
    с
    1.51
    POSITIVE LOGITS
    ל
    2.73
    ことです
    1.93
     calda
    1.91
    Promises
    1.91
    ﺍ
    1.88
    ະ
    1.88
     dotycz
    1.86
    Episode
    1.84
    SEN
    1.84
    ان
    1.80
    Activations Density 0.027%

    No Known Activations