© 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-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 7424
    Prev
    Next
    INDEX
    Explanations

    radians, Genesis, nucleus, Spain, genes, Rhys

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    та
    2.69
     grosses
    1.66
     pretzels
    1.48
    ш
    1.47
    йна
    1.46
     pellets
    1.45
     casework
    1.40
    ים
    1.34
     skis
    1.34
     hybrids
    1.34
    POSITIVE LOGITS
    m
    2.31
    i
    2.25
    lardan
    2.13
    er
    2.08
    ming
    1.93
    y
    1.86
    ların
    1.78
    madı
    1.78
    ması
    1.77
    muse
    1.77
    Activations Density 0.001%

    No Known Activations