© 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. 9573
    Prev
    Next
    INDEX
    Explanations

    need or necessity

    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
     kuma
    0.83
     sách
    0.80
     Đoàn
    0.79
    語
    0.79
     paket
    0.78
    ppings
    0.77
     kab
    0.76
     poetry
    0.75
     sehingga
    0.75
    稅
    0.75
    POSITIVE LOGITS
    umno
    0.84
    ARRY
    0.80
    ал
    0.79
    ार
    0.77
    AIN
    0.74
    संघ
    0.74
    ars
    0.74
    лік
    0.74
    AL
    0.73
    ानुसार
    0.73
    Activations Density 0.000%

    No Known Activations