© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 2106
    Prev
    Next
    INDEX
    Explanations

    script with, silhouette with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
     tandis
    1.32
    이며
    1.19
    ։
    1.19
    。.
    1.18
     sedangkan
    1.18
     Sedangkan
    1.18
    。\
    1.17
    ค่ะ
    1.16
    。...
    1.16
    သည်။
    1.12
    POSITIVE LOGITS
    —
    0.88
     merely
    0.87
     simply
    0.87
     not
    0.87
     essentially
    0.85
     basically
    0.83
     unwittingly
    0.80
     astray
    0.80
     somehow
    0.80
     repeatedly
    0.79
    Activations Density 0.204%

    No Known Activations