© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 4189
    Prev
    Next
    INDEX
    Explanations

    Key improvements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
    )=$
    1.28
    }=$
    1.19
     espacial
    1.12
     doméstica
    1.10
    $/.
    1.09
    }}$
    1.09
    CRETE
    1.07
    -}$
    1.07
    aptops
    1.07
     grained
    1.07
    POSITIVE LOGITS
     Carn
    1.32
     Bro
    1.16
    Carn
    1.14
     Carnival
    1.12
     Cra
    1.12
     paras
    1.12
     Cir
    1.08
     Bloc
    1.08
    Cir
    1.06
     Paras
    1.06
    Activations Density 0.092%

    No Known Activations