© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 7322
    Prev
    Next
    INDEX
    Explanations

    vegetables and numbered lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_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
     naby
    0.80
     getContent
    0.78
    족
    0.77
    }});
    0.75
    ]],
    0.72
    genza
    0.71
    uant
    0.71
    ^{*}}
    0.70
     দফা
    0.69
     সন্ত
    0.69
    POSITIVE LOGITS
    şehir
    0.98
    ভাস
    0.95
    agnar
    0.94
     balt
    0.92
     Bremer
    0.92
    Schwarz
    0.90
    rine
    0.89
     hooded
    0.89
    Code
    0.88
     code
    0.88
    Activations Density 0.007%

    No Known Activations