© 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. 34-GEMMASCOPE-RES-131K
    7. 106557
    Prev
    Next
    INDEX
    Explanations

    unique

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

    The neuron flags occurrences of the root “uniqu-,” i.e. the word “unique” and its related forms (uniqueness, uniqueItems, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    าน
    -0.92
     PDB
    -0.84
     ODI
    -0.81
     DOM
    -0.80
     VEGF
    -0.79
     ung
    -0.78
    ürlich
    -0.78
    挤
    -0.77
    蓁
    -0.77
     largement
    -0.76
    POSITIVE LOGITS
     obfer
    0.94
     occafion
    0.90
    tative
    0.90
    ᆨ
    0.83
    consulta
    0.82
    arpa
    0.77
     taba
    0.77
     カバー
    0.77
    esss
    0.77
     neceff
    0.76
    Activations Density 0.015%

    No Known Activations