© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 15743
    Prev
    Next
    INDEX
    Explanations

    .org, .edu, URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
    عات
    0.78
    ших
    0.71
    വ
    0.70
    قق
    0.69
     financed
    0.68
    вал
    0.68
    গা
    0.68
    ppa
    0.67
    ф
    0.67
    কাল
    0.66
    POSITIVE LOGITS
     القدر
    1.03
     возможность
    0.92
     אַ
    0.85
     informiert
    0.84
     aby
    0.83
     zewnętr
    0.82
     deste
    0.82
     asistencia
    0.82
     proveedor
    0.82
     ito
    0.81
    Activations Density 0.001%

    No Known Activations