© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 37380
    Prev
    Next
    INDEX
    Explanations

    workers, jobs, time

    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
    ل
    1.38
    speople
    1.09
     riddled
    1.08
     reassuring
    0.99
    と考えて
    0.98
    两大
    0.98
     renowned
    0.97
    לת
    0.97
    arse
    0.94
     multifaceted
    0.93
    POSITIVE LOGITS
    j
    1.21
     armes
    1.15
     coalgebras
    1.13
     habitaciones
    1.11
    tuples
    1.09
     وعلى
    1.08
    𝐭
    1.07
    been
    1.05
     escritos
    1.05
    דה
    1.05
    Activations Density 0.001%

    No Known Activations