© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 40386
    Prev
    Next
    INDEX
    Explanations

    high quality appraisal

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

    The neuron fires strongly on capitalized named entities—people’s names, titles, places, years, 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_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
    lccc
    -1.02
    はコチラ
    -1.01
     here
    -0.99
     dårlig
    -0.94
    ceptable
    -0.92
    HttpStatusCode
    -0.92
    victory
    -0.90
    Typeface
    -0.89
    はこちらから
    -0.89
     adanya
    -0.88
    POSITIVE LOGITS
     excellence
    1.29
     superb
    1.26
     exceptional
    1.16
     فوق
    1.09
     excellent
    1.09
     quality
    1.07
     Superb
    1.07
     outstanding
    1.06
    Outstanding
    1.05
    outstanding
    1.05
    Activations Density 0.154%

    No Known Activations