© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-16K
    7. 3857
    Prev
    Next
    INDEX
    Explanations

    7 score / MMSE score

    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_24_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
    欸
    0.79
    ifferentiated
    0.69
     harnessed
    0.68
     tireless
    0.68
    чайно
    0.68
     назем
    0.67
     iconic
    0.67
    }{\
    0.66
    ar
    0.66
    illiant
    0.66
    POSITIVE LOGITS
    د
    0.83
     خپل
    0.80
     Questo
    0.76
    middlewares
    0.75
    幵
    0.75
    mA
    0.75
    Hozzáférés
    0.75
    dX
    0.74
    mot
    0.73
    Կ
    0.72
    Activations Density 0.004%

    No Known Activations