© 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. 41303
    Prev
    Next
    INDEX
    Explanations

    years or decades

    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
    ’,
    0.91
    roidism
    0.90
    一些
    0.87
     cruise
    0.87
     alleles
    0.84
    inheritDoc
    0.83
    <0xAE>
    0.82
    рий
    0.82
    loride
    0.82
     posti
    0.82
    POSITIVE LOGITS
    ع
    1.23
    ﻴ
    1.21
    ﺮ
    1.19
    𝗘
    1.18
    ﻁ
    1.13
    𝗔
    1.09
    ﺹ
    1.09
    ﻌ
    1.06
    s
    1.05
    ﺘ
    1.05
    Activations Density 0.022%

    No Known Activations