© 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-3-1B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 3265
    Prev
    Next
    INDEX
    Explanations

    game changer, transformation, revolution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_17_width_16k_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
     adds
    0.80
     extender
    0.77
     added
    0.75
     add
    0.75
     supplemental
    0.73
     adding
    0.72
     Adding
    0.71
     精
    0.71
     Bonus
    0.71
    Supplementary
    0.69
    POSITIVE LOGITS
     transformative
    1.82
     transformation
    1.80
     change
    1.75
     Change
    1.74
     revolution
    1.74
    transformation
    1.73
    变革
    1.73
     transformación
    1.69
    Change
    1.68
     transformação
    1.68
    Activations Density 0.607%

    No Known Activations