© 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. 15746
    Prev
    Next
    INDEX
    Explanations

    recognition, pins, items, authenticate

    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
    ampionship
    0.78
    ylinder
    0.75
    assembling
    0.73
    ímica
    0.71
    。
    0.71
    airy
    0.71
    ทั้งหมด
    0.70
    }$.
    0.69
    ształ
    0.69
    omega
    0.68
    POSITIVE LOGITS
     redesignated
    0.84
     socioeconomic
    0.70
     transitioned
    0.68
     Caucasian
    0.66
     Northeast
    0.66
     South
    0.65
     neoliberal
    0.64
     /$
    0.64
    ಡೆಯ
    0.64
     understandings
    0.63
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.