© 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. 4133
    Prev
    Next
    INDEX
    Explanations

    publisher publishing

    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
     gets
    1.14
    1.12
     or
    1.09
     equates
    1.05
     joystick
    1.03
     curfew
    0.99
     thinks
    0.97
     व
    0.96
     essayé
    0.95
     comes
    0.95
    POSITIVE LOGITS
     Publishers
    1.27
    Publish
    1.15
    publisher
    1.04
    出版
    1.02
    𝑬
    1.01
    ISBN
    0.99
     Publishing
    0.98
     publishers
    0.98
    Else
    0.96
    Publication
    0.96
    Activations Density 0.059%

    No Known Activations