© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 11570
    Prev
    Next
    INDEX
    Explanations

    largest number, runs in, sum of, concatenate

    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
     querida
    1.00
     Ở
    0.96
     now
    0.89
     នៅ
    0.86
     being
    0.86
     මේ
    0.86
     December
    0.82
     මෙ
    0.82
     परंपरा
    0.82
     hôm
    0.81
    POSITIVE LOGITS
    apsack
    0.89
    äns
    0.85
     a
    0.80
    apest
    0.79
     а
    0.78
     keltiradi
    0.77
    bbing
    0.77
    )
    0.75
    \
    0.75
    лект
    0.74
    Activations Density 0.314%

    No Known Activations