© 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. 11447
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    س
    0.88
    ipping
    0.88
    ص
    0.86
    nen
    0.84
    S
    0.84
    IP
    0.82
    sl
    0.80
    N
    0.77
    AR
    0.76
    IME
    0.75
    POSITIVE LOGITS
     ombil
    1.07
     машиналарын
    1.01
     bicarbon
    1.00
     prostagland
    0.99
     nécessairement
    0.97
     sincron
    0.95
     више
    0.94
     incess
    0.94
     striées
    0.94
     nécess
    0.93
    Activations Density 0.000%

    No Known Activations