© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 3474
    Prev
    Next
    INDEX
    Explanations

    categorized by

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects descriptions of buildings or rooms being raised on stilts or constructed like treehouses.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    。
    1.44
    .");
    1.23
    。『
    1.20
    "/>.
    1.20
    }$.
    1.13
    。「
    1.13
    .";
    1.13
    .';
    1.13
    }.
    1.12
     。
    1.10
    POSITIVE LOGITS
    ),
    1.59
    ?,
    1.52
    ?),
    1.45
    ）,
    1.34
    )，
    1.33
    ),\
    1.32
    )،
    1.31
     ),
    1.30
     ?,
    1.30
     [],
    1.29
    Activations Density 0.222%

    No Known Activations