© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 37807
    Prev
    Next
    INDEX
    Explanations

    see what happens next

    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_262k_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
     forbade
    1.16
     heirloom
    1.11
     tampa
    1.11
    。
    1.10
     mellitus
    1.08
     позднее
    1.05
    もっと
    1.03
     confid
    1.02
    ﮨ
    1.02
     crucified
    1.01
    POSITIVE LOGITS
    ut
    1.20
    ün
    1.09
    ž
    1.05
    ło
    1.04
    Creo
    1.02
    pp
    0.99
    ge
    0.98
    İN
    0.98
    tter
    0.97
    ii
    0.95
    Activations Density 0.009%

    No Known Activations