© 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. 10477
    Prev
    Next
    INDEX
    Explanations

    used,mentionedchampioned

    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
    ↵↵
    0.94
    有一
    0.85
     ў
    0.83
    です
    0.83
     یې
    0.82
     goalkeeper
    0.81
     específ
    0.80
     Editar
    0.79
     vítima
    0.79
     número
    0.78
    POSITIVE LOGITS
    i
    1.01
     i
    0.93
    seudo
    0.82
     it
    0.81
     if
    0.80
    wirkungen
    0.79
    posterous
    0.79
    s
    0.79
    ?")
    0.79
    ﻝ
    0.79
    Activations Density 0.889%

    No Known Activations