© 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. 10710
    Prev
    Next
    INDEX
    Explanations

    named entities followed by descriptors

    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
    uradaki
    0.68
    𝗮
    0.66
     एंड्रॉयड
    0.65
    ամ
    0.64
    orschungs
    0.63
    ιου
    0.62
    testAvg
    0.61
     radiology
    0.59
    orgetown
    0.59
     तपाई
    0.58
    POSITIVE LOGITS
     has
    0.74
    )
    0.72
    ↵
    0.71
     of
    0.70
    >
    0.65
     was
    0.64
     are
    0.63
     is
    0.63
     by
    0.62
     have
    0.62
    Activations Density 0.123%

    No Known Activations