© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 7905
    Prev
    Next
    INDEX
    Explanations

    I'm not sure

    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_12_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
    ettle
    1.57
    érg
    1.54
     čl
    1.45
    fit
    1.43
     birdies
    1.42
    elernt
    1.39
    -
    1.36
    }?
    1.36
    fon
    1.34
    ốn
    1.34
    POSITIVE LOGITS
     governo
    1.96
     bureaucracy
    1.94
     pemerintah
    1.92
     gior
    1.92
    itoare
    1.89
     gouvernement
    1.87
     rumours
    1.85
     craziness
    1.85
     stupidity
    1.84
     notícias
    1.83
    Activations Density 0.065%

    No Known Activations