© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-16K
    4. 5667
    Prev
    Next
    INDEX
    Explanations

    specific prefixes leading to different languages

    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_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
    ו
    1.63
    cello
    1.22
     وبال
    1.21
    IRE
    1.20
    ic
    1.17
    ларга
    1.16
    cakes
    1.16
    ن
    1.15
    ER
    1.14
    лаб
    1.14
    POSITIVE LOGITS
    ]);}
    1.22
    3
    1.19
     estar
    1.17
    </tbody>
    1.16
     diretta
    1.16
     kerap
    1.14
    ります
    1.13
     tivesse
    1.12
    5
    1.11
     stessi
    1.10
    Activations Density 0.027%

    No Known Activations