© 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. 24-GEMMASCOPE-2-RES-16K
    7. 11320
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    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
    젹
    0.81
    किस
    0.76
    ış
    0.70
    owel
    0.69
    rl
    0.67
    oka
    0.67
    erek
    0.65
    isk
    0.65
    unak
    0.65
     \\
    0.64
    POSITIVE LOGITS
     ABO
    0.88
     beatae
    0.84
    י
    0.82
     Merton
    0.80
    臨界
    0.78
     Angola
    0.75
     swaps
    0.75
    ﻒ
    0.73
     Arma
    0.73
     Calabria
    0.72
    Activations Density 0.002%

    No Known Activations