© 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. 7-GEMMASCOPE-2-RES-16K
    7. 213
    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_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
    <unused298>
    0.69
    intrinsic
    0.68
    syst
    0.68
    angled
    0.67
    findBy
    0.66
    adjust
    0.65
    singular
    0.65
    exact
    0.64
    seekg
    0.64
    zmdi
    0.64
    POSITIVE LOGITS
     T
    0.81
     C
    0.81
     Κ
    0.80
     Ν
    0.79
     Beach
    0.78
     Norte
    0.78
     Ε
    0.78
     Α
    0.78
     Ρ
    0.78
     Restaurant
    0.77
    Activations Density 3.420%

    No Known Activations