© 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. 10-GEMMASCOPE-RES-131K
    4. 75478
    Prev
    Next
    INDEX
    Explanations

    website formatting and technical issues

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

    The neuron fires on that common meta-comment “My pics aren’t loaded up right now so I can’t show them to you,” i.e. text explaining that images aren’t available.

    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
    During
    -1.44
    ğmen
    -1.30
    Équipe
    -1.30
    Spesifikasi
    -1.29
    neko
    -1.26
     ennen
    -1.26
    Between
    -1.24
     pazi
    -1.23
    However
    -1.23
     Herramientas
    -1.23
    POSITIVE LOGITS
     you
    1.85
     my
    1.67
     it
    1.34
     me
    1.08
     on
    1.06
     this
    1.05
     i
    1.05
    vaných
    1.03
    ítulos
    1.01
    OFFER
    1.00
    Activations Density 0.229%

    No Known Activations