© 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. 42294
    Prev
    Next
    INDEX
    Explanations

    Old Fashioned, Old Tom, weather, miles

    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
    ập
    0.99
    }}^{-
    0.89
    apat
    0.86
    ively
    0.85
    운
    0.85
    nią
    0.83
    ated
    0.82
    }
    0.82
    ives
    0.82
    unci
    0.81
    POSITIVE LOGITS
    ب
    1.02
    ሶች
    0.80
    Ц
    0.77
    ات
    0.77
     chagrin
    0.77
    س
    0.75
    től
    0.74
    disposing
    0.73
    コットン
    0.73
    Я
    0.72
    Activations Density 0.001%

    No Known Activations