© 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. 40700
    Prev
    Next
    INDEX
    Explanations

    Donbas

    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
    ки
    1.11
    ier
    1.05
    นี้
    1.00
     occurs
    0.95
    জগতের
    0.95
    ﻤ
    0.95
    ти
    0.93
    ﻘ
    0.92
    จาก
    0.91
     isIn
    0.91
    POSITIVE LOGITS
     Miners
    0.88
     parlé
    0.85
    stride
    0.82
    ن
    0.80
     Brexit
    0.79
    elés
    0.79
    ビング
    0.77
     Sheffield
    0.77
    jän
    0.76
     časti
    0.76
    Activations Density 0.003%

    No Known Activations