© 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. 10278
    Prev
    Next
    INDEX
    Explanations

    enough to

    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
    ties
    1.84
    ized
    1.83
    1.70
    llä
    1.66
    ة
    1.66
    oids
    1.56
    너지
    1.51
    icrobial
    1.49
    ći
    1.47
     назначен
    1.47
    POSITIVE LOGITS
    س
    2.83
    م
    2.73
    ı
    2.67
    ের
    2.66
    s
    2.66
    те
    2.53
    т
    2.47
    жа
    2.44
    ल
    2.36
    ни
    2.34
    Activations Density 0.007%

    No Known Activations