© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 34160
    Prev
    Next
    INDEX
    Explanations

    math, medical, vehicles, and people context

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

    The neuron activates for common nouns that could be the subject of a sentence, particularly those referring to physical objects, people, or entities.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }$.
    -1.66
    ());
    
    -1.60
    ());
    -1.54
    .");
    -1.48
    ()));
    -1.46
    ()];
    -1.44
     \%$.
    -1.41
    .‏
    -1.38
    ®.
    -1.38
    ];
    -1.35
    POSITIVE LOGITS
     will
    2.09
    が
    1.77
     can
    1.70
     should
    1.67
     of
    1.63
     must
    1.53
     have
    1.51
     are
    1.41
     CANNOT
    1.41
     would
    1.38
    Activations Density 0.146%

    No Known Activations