© 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
    2. Gemma-3-4B
    3. 29-GEMMASCOPE-2-RES-16K
    4. 2102
    Prev
    Next
    INDEX
    Explanations

    section headings or titles

    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
     。,
    1.24
     }}$,
    1.22
     }}$.
    1.19
    }.}
    1.07
    )$,
    1.05
     、,
    1.03
    }}$.
    1.03
    }$).
    1.03
    )}$,
    1.03
    。</
    1.00
    POSITIVE LOGITS
     overview
    1.70
     Overview
    1.44
     revisited
    1.37
     Explained
    1.36
     explained
    1.34
     vs
    1.32
     summary
    1.25
     &
    1.24
     via
    1.24
     versus
    1.24
    Activations Density 0.267%

    No Known Activations