© 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. 41433
    Prev
    Next
    INDEX
    Explanations

    addiction, assumption, dealing with, tomorrow, boards

    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
     acciaio
    0.84
     alcun
    0.84
     SPARSE
    0.84
     अभिकारक
    0.83
    これは
    0.83
    嚧
    0.82
     capa
    0.82
     couplers
    0.82
     MANUFACT
    0.80
     fabricant
    0.80
    POSITIVE LOGITS
    m
    0.94
    le
    0.77
    h
    0.75
    0.75
    ch
    0.74
    o
    0.73
    м
    0.73
    数据显示
    0.71
    ying
    0.70
    iding
    0.68
    Activations Density 0.000%

    No Known Activations