© 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-262K
    7. 11273
    Prev
    Next
    INDEX
    Explanations

    tasks and duties

    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
    n
    1.20
    ą
    1.03
    sound
    1.02
    m
    1.00
    down
    0.96
    ta
    0.96
    án
    0.93
    band
    0.92
    ek
    0.88
     n
    0.87
    POSITIVE LOGITS
     tasks
    1.60
     tarefas
    1.43
     chores
    1.42
     tareas
    1.39
     Tasks
    1.38
     duties
    1.38
     errands
    1.38
     funções
    1.35
     tarefa
    1.35
     functions
    1.33
    Activations Density 0.690%

    No Known Activations