© 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. 12130
    Prev
    Next
    INDEX
    Explanations

    `createElement` or `venv` or `pip`

    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
     indígen
    1.39
     فیصلہ
    1.38
     designee
    1.36
     pueda
    1.33
     appellants
    1.31
     paperback
    1.30
     cornea
    1.28
    餬
    1.28
     poesía
    1.27
    此之外
    1.27
    POSITIVE LOGITS
    y
    2.44
    te
    2.02
    ي
    1.85
    י
    1.77
    i
    1.73
    h
    1.72
    l
    1.54
    o
    1.51
    er
    1.49
    e
    1.49
    Activations Density 0.057%

    No Known Activations