© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 84671
    Prev
    Next
    INDEX
    Explanations

    media formats and versions

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

    The neuron fires on mentions of physical media formats and their versions (e.g. “BD,” “DVD,” “CD”) often in the context of comparing releases.

    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
     support
    -1.09
     training
    -1.05
     during
    -1.04
    }{@
    -1.04
     we
    -1.03
     sustainable
    -1.02
     style
    -1.01
     Wednesday
    -1.00
    furan
    -1.00
     in
    -0.98
    POSITIVE LOGITS
     culte
    1.26
     coffret
    1.21
     docteur
    1.13
    Amazon
    1.12
    utsches
    1.09
     épu
    1.08
     Discogs
    1.06
     espoir
    1.06
     seny
    1.05
    匮
    1.05
    Activations Density 0.040%

    No Known Activations