© 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-16K
    7. 9808
    Prev
    Next
    INDEX
    Explanations

    secret society, code, romance, exchange

    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
    एस
    2.16
    ı
    2.05
    ے
    1.81
    ü
    1.77
    ut
    1.76
    om
    1.74
    いき
    1.74
    ae
    1.70
    та
    1.66
    ್
    1.64
    POSITIVE LOGITS
    값
    2.14
    اعری
    2.02
     Dupree
    1.85
     вопроса
    1.82
    Մ
    1.78
    ການ
    1.77
    페이지
    1.77
    Վ
    1.75
    값을
    1.73
    РО
    1.73
    Activations Density 0.069%

    No Known Activations