© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 3216
    Prev
    Next
    INDEX
    Explanations

    around, beneath, alongside

    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
     siku
    1.63
    IMIENTO
    1.51
     discapacidad
    1.50
     finalidad
    1.49
    を用いる
    1.49
    "])
    1.47
     jd
    1.45
    )']
    1.45
    lifetime
    1.44
     afecta
    1.43
    POSITIVE LOGITS
     stacks
    2.07
    窸
    1.81
     shelves
    1.80
     shadowy
    1.79
     neatly
    1.78
     rows
    1.76
     strewn
    1.76
     clustered
    1.76
     khaki
    1.74
     stacked
    1.72
    Activations Density 0.223%

    No Known Activations