© 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. 4647
    Prev
    Next
    INDEX
    Explanations

    String processing

    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
    le
    1.48
    ك
    1.35
    ट
    1.28
    b
    1.21
    G
    1.21
    u
    1.13
    кої
    1.05
    ل
    1.05
    :
    1.05
    uito
    1.04
    POSITIVE LOGITS
     scriptures
    1.02
     priesthood
    1.02
     therapies
    0.96
     Дэ
    0.96
     surgeries
    0.95
    addKill
    0.89
     stedet
    0.89
    iota
    0.88
     pesantren
    0.88
     syukur
    0.87
    Activations Density 0.033%

    No Known Activations