© 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. 30310
    Prev
    Next
    INDEX
    Explanations

    explaining concepts or definitions

    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
     currentRow
    0.80
    קר
    0.80
    ğun
    0.77
    suit
    0.75
    ційний
    0.73
     પ
    0.72
    מא
    0.70
    train
    0.69
    evole
    0.68
    satellite
    0.68
    POSITIVE LOGITS
     Probate
    0.89
     accession
    0.84
    ology
    0.82
     Presse
    0.81
     Politik
    0.80
     Ges
    0.79
    </a>
    0.78
     निकालते
    0.78
     Teknik
    0.77
     Physik
    0.77
    Activations Density 0.000%

    No Known Activations