© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2641
    Prev
    Next
    INDEX
    Explanations

    benefits of X

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     interferes
    1.66
     interfere
    1.50
     seams
    1.35
     interfered
    1.34
     unsound
    1.33
    臬
    1.23
     regulates
    1.23
    纲
    1.22
     disturbs
    1.21
     않으면
    1.20
    POSITIVE LOGITS
     бонус
    2.07
     cadeau
    2.01
     Rewards
    2.00
     regalo
    1.93
     penghargaan
    1.91
     rebate
    1.88
    bonus
    1.88
     cashback
    1.84
    Bonus
    1.84
     rewards
    1.83
    Activations Density 0.903%

    No Known Activations