© 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. 13345
    Prev
    Next
    INDEX
    Explanations

    healthy relationships and coping

    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
    speople
    2.55
    न
    1.99
    ের
    1.77
    sız
    1.62
    िक
    1.59
    sons
    1.57
    ے
    1.55
    ны
    1.53
    ா
    1.52
    satz
    1.49
    POSITIVE LOGITS
    足り
    1.51
    taining
    1.49
    を経て
    1.48
    지만
    1.48
    丕
    1.48
    居然
    1.47
    ﺓ
    1.44
    的值
    1.43
    ที่จะ
    1.41
     relinqu
    1.41
    Activations Density 0.070%

    No Known Activations