© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84011
    Prev
    Next
    INDEX
    Explanations

    cosmological redshift

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

    The neuron specifically fires on technical astrophysics terminology—especially mentions of redshift measurements and quasar absorption systems.

    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
    !
    -1.65
     wann
    -1.59
    뻗
    -1.52
    麁
    -1.52
    などは
    -1.49
    ᐅ
    -1.49
     circonstances
    -1.48
    étranger
    -1.45
    ・「
    -1.45
    θλη
    -1.42
    POSITIVE LOGITS
    0
    2.05
     innego
    1.82
    8
    1.60
    2
    1.55
    沮
    1.55
    3
    1.54
    6
    1.54
    7
    1.50
    ’
    1.43
    áu
    1.40
    Activations Density 0.018%

    No Known Activations