© 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. 4389
    Prev
    Next
    INDEX
    Explanations

    already

    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
    ik
    1.84
    )
    1.79
    {
    1.79
    es
    1.67
    ling
    1.66
    }
    1.61
    ler
    1.56
    ly
    1.55
    )}}
    1.55
     Tans
    1.52
    POSITIVE LOGITS
    Е
    2.02
    𝘾
    2.00
     давно
    1.91
     Deshalb
    1.80
    arif
    1.78
    сто
    1.77
    ة
    1.77
    р
    1.75
    рей
    1.71
    РА
    1.71
    Activations Density 0.101%

    No Known Activations