© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14024
    Prev
    Next
    INDEX
    Explanations

    Cohen

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

    The neuron spots occurrences of the proper name “Cohen,” especially in author or citation contexts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     amazingly
    -3.13
    
    -2.92
    ll
    -2.84
     immense
    -2.83
     gorgeous
    -2.73
     dont
    -2.73
     amazing
    -2.72
     elaborate
    -2.72
     extremely
    -2.70
    各样的
    -2.70
    POSITIVE LOGITS
    𖥧
    2.95
    薷
    2.80
    </b>
    2.58
    }$
    2.58
    "},
    2.45
    èvent
    2.44
    😇
    2.42
    </td>
    2.42
    to
    2.38
    龱
    2.30
    Activations Density 0.002%

    No Known Activations