© 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. 24-GEMMASCOPE-2-RES-16K
    7. 5041
    Prev
    Next
    INDEX
    Explanations

    starting or turning

    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_24_width_16k_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
    溃
    0.77
    ない
    0.72
     loro
    0.70
    нити
    0.68
    的风
    0.67
    ClientId
    0.66
    일을
    0.66
    meno
    0.66
     뽑
    0.65
    Voir
    0.64
    POSITIVE LOGITS
     seman
    0.83
    畛
    0.82
     simplices
    0.81
     Moderna
    0.78
     vacuoles
    0.78
     පුද්ග
    0.77
     Springs
    0.77
     amazement
    0.76
     credence
    0.75
     piercings
    0.75
    Activations Density 0.001%

    No Known Activations