© 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. 12-GEMMASCOPE-2-RES-262K
    7. 42276
    Prev
    Next
    INDEX
    Explanations

    explicitly, fluidly, macro

    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
    我
    0.92
    隅
    0.86
     possono
    0.84
     semplicemente
    0.83
    અ
    0.83
     ίδια
    0.82
    躍
    0.82
    業界
    0.81
     різні
    0.81
    আ
    0.80
    POSITIVE LOGITS
     crowned
    0.88
     undet
    0.76
     turnovers
    0.75
     infile
    0.73
     Normalize
    0.72
     attributed
    0.71
     singly
    0.71
    जात
    0.71
     ظِلِّ
    0.70
     দ্বিত
    0.70
    Activations Density 0.000%

    No Known Activations