© 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. 41905
    Prev
    Next
    INDEX
    Explanations

    Marcus Aurelius and Google Keyword Planner

    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
    특별시
    1.99
    sdale
    1.41
    ﻮ
    1.26
    ుల
    1.22
    site
    1.20
    sz
    1.13
    &=\
    1.13
    sing
    1.12
    ்களை
    1.12
    ்களில்
    1.12
    POSITIVE LOGITS
    fox
    1.36
     immobilized
    1.34
    خ
    1.34
    fuck
    1.31
    лы
    1.24
     idealized
    1.24
    ва
    1.21
    fas
    1.19
     maximize
    1.19
    f
    1.18
    Activations Density 0.000%

    No Known Activations