© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 16057
    Prev
    Next
    INDEX
    Explanations

    essential oils

    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
    Π
    1.40
    h
    1.15
    ir
    1.14
    ج
    1.13
    ed
    1.12
    L
    1.10
    n
    1.09
    ͕
    1.09
    is
    1.06
    д
    1.06
    POSITIVE LOGITS
    峤
    1.00
    ForRule
    0.99
    까요
    0.96
    اونلو
    0.93
    च्चय
    0.93
    児
    0.93
    selves
    0.92
     рождения
    0.89
     bergabung
    0.89
    ानुसार
    0.87
    Activations Density 0.018%

    No Known Activations