© 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. 72664
    Prev
    Next
    INDEX
    Explanations

    Proper nouns and identifiers

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

    The neuron fires strongly on capitalized proper names (i.e. person names).

    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
    </strong>
    -3.44
    id
    -2.86
     dismal
    -2.72
    c
    -2.64
    </u>
    -2.63
     sumptuous
    -2.58
     shrewd
    -2.55
     dreary
    -2.50
     deliciously
    -2.45
     horrifying
    -2.44
    POSITIVE LOGITS
    骓
    3.19
    𖡼
    2.89
    踯
    2.66
    er
    2.52
     granada
    2.52
    $
    2.50
    靺
    2.50
     salvador
    2.48
     portugu
    2.47
     tigre
    2.44
    Activations Density 0.004%

    No Known Activations