© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 879
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    —”
    1.39
     (…)
    1.36
    ”—
    1.32
     yalnızca
    1.27
    “[
    1.26
    —“
    1.26
     TikTok
    1.23
    ,’”
    1.21
    🫶
    1.20
    —
    1.20
    POSITIVE LOGITS
     alot
    1.73
     muß
    1.48
     coment
    1.39
     loosing
    1.37
     teh
    1.37
     compd
    1.35
     thru
    1.35
     IMHO
    1.32
     dont
    1.31
     kinda
    1.30
    Activations Density 2.314%

    No Known Activations