© 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. 12701
    Prev
    Next
    INDEX
    Explanations

    eca

    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
    lah
    1.38
    و
    1.13
    elijk
    1.13
     étab
    1.10
    ról
    1.09
     রকম
    1.09
    ل
    1.09
    na
    1.08
    lac
    1.07
    azione
    1.05
    POSITIVE LOGITS
     humiliated
    1.10
     disputed
    1.09
     elbow
    1.08
    udge
    1.07
     pilgrimage
    1.05
    çe
    1.04
     deactivated
    1.03
     forbade
    1.03
     accented
    1.02
    প
    1.02
    Activations Density 0.004%

    No Known Activations