© 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. 12616
    Prev
    Next
    INDEX
    Explanations

    harmful principle following data

    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
     transcendent
    1.78
     canton
    1.75
     delineated
    1.71
     madad
    1.71
     exceeds
    1.67
     opulent
    1.61
    ეგისტრ
    1.61
    斓
    1.61
    না
    1.60
    ᾷ
    1.59
    POSITIVE LOGITS
    ICSS
    1.35
    ti
    1.27
    estal
    1.23
    UGHT
    1.23
    ころ
    1.20
    folge
    1.18
     Dich
    1.18
    tss
    1.17
    tra
    1.16
    RY
    1.15
    Activations Density 19.908%

    No Known Activations