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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 827
    Prev
    Next
    INDEX
    Explanations

    food, nature, summer, good, real

    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
     berupa
    1.22
    。
    1.21
    EN
    1.09
    なる
    1.05
    sächlich
    1.03
    Những
    1.02
    Orden
    1.01
    screw
    1.01
    Proble
    1.01
    Bộ
    1.01
    POSITIVE LOGITS
     ​​
    1.12
    творю
    1.09
     oranges
    1.06
     accounted
    1.01
    री
    1.00
     advancing
    1.00
    anje
    0.99
     stagnant
    0.97
     cost
    0.96
    িয়া
    0.96
    Activations Density 0.011%

    No Known Activations