© 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. 22-GEMMASCOPE-RES-131K
    7. 15903
    Prev
    Next
    INDEX
    Explanations

    names and words following them

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

    The neuron is looking for proper nouns (title-cased names and other capitalized entities).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     favoris
    -1.01
    Према
    -1.00
     飾
    -0.91
    ESSMENT
    -0.91
     sáb
    -0.88
     consumidor
    -0.86
    landır
    -0.85
     cív
    -0.85
     ц
    -0.84
    ródła
    -0.84
    POSITIVE LOGITS
     construite
    1.16
    ęcz
    0.81
    ствием
    0.81
     られ
    0.81
    дитесь
    0.80
     incluse
    0.79
     velik
    0.79
    ,
    0.79
    をします
    0.79
     eventuell
    0.79
    Activations Density 0.030%

    No Known Activations