© 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. 22-GEMMASCOPE-RES-131K
    7. 16398
    Prev
    Next
    INDEX
    Explanations

    locations and conditions

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

    The neuron fires strongly on numeric expressions and associated units (e.g. counts, durations, years, times).

    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
     
    -1.14
    なのでしょう
    -1.04
    }}-
    -1.02
    npmjs
    -1.01
    他也
    -0.98
    もある
    -0.97
    看看
    -0.97
    信心
    -0.96
     olmayan
    -0.95
    hradun
    -0.92
    POSITIVE LOGITS
     any
    1.55
     qualquer
    1.25
    任何
    1.20
     cualquier
    1.18
     даже
    1.17
     qualsiasi
    1.14
     aparcamiento
    1.09
     дори
    1.09
     навіть
    1.09
     unless
    1.08
    Activations Density 0.018%

    No Known Activations