© 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
    5. 13-GEMMASCOPE-2-RES-16K
    7. 915
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
    oworld
    1.16
    잿
    1.11
     erupted
    1.09
    eweg
    1.08
     amazed
    1.06
     Hooker
    1.05
    やはり
    1.04
    ewood
    1.03
    轟
    1.02
    ansk
    1.02
    POSITIVE LOGITS
     bonus
    1.95
     Bonus
    1.88
     exemption
    1.85
     Eligible
    1.84
    Bonus
    1.79
     BONUS
    1.78
    bonus
    1.77
     cashback
    1.72
     eligible
    1.71
    Elig
    1.69
    Activations Density 3.269%

    No Known Activations