© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 1219
    Prev
    Next
    INDEX
    Explanations

    URLs and LaTeX commands

    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_31_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
    ](#
    0.71
    </tbody>
    0.65
    in
    0.63
    ](
    0.61
     ]
    0.61
    </ul>
    0.59
    utip
    0.58
    ](/
    0.58
    ].
    0.57
     cited
    0.56
    POSITIVE LOGITS
    ianic
    0.68
     designer
    0.62
     hué
    0.59
     shapes
    0.59
     Ahn
    0.59
     escalas
    0.57
     aconsel
    0.57
     personalità
    0.57
     sociable
    0.56
    {},
    0.56
    Activations Density 0.038%

    No Known Activations