© 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. 10-GEMMASCOPE-RES-131K
    7. 67283
    Prev
    Next
    INDEX
    Explanations

    numbers after 'day'

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

    The neuron never activates on any token—i.e. it doesn’t detect any pattern.

    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
    cking
    -2.36
    vantaged
    -2.23
    ters
    -2.20
    pherals
    -2.17
    lossians
    -2.16
    猛地
    -2.06
    aient
    -2.06
    versaire
    -2.03
    ck
    -2.02
    bie
    -2.00
    POSITIVE LOGITS
     and
    3.42
     at
    2.67
     it
    2.64
     this
    2.52
     that
    2.38
     always
    2.38
     with
    2.30
     every
    2.27
     then
    2.25
     caused
    2.20
    Activations Density 0.079%

    No Known Activations