© 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. 10900
    Prev
    Next
    INDEX
    Explanations

    names for variables and other code elements

    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
     CLIENTI
    1.31
    ఆ
    1.29
    व
    1.27
     antérieure
    1.27
     reuniones
    1.25
    ઔ
    1.24
    о
    1.22
    ⺈
    1.22
     τε
    1.21
    部队
    1.20
    POSITIVE LOGITS
    ia
    1.65
    ,
    1.48
    ine
    1.38
     nephew
    1.38
    nce
    1.36
     unsurprisingly
    1.34
    ish
    1.26
    ani
    1.26
    ned
    1.26
    esi
    1.24
    Activations Density 0.003%

    No Known Activations