© 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. 6983
    Prev
    Next
    INDEX
    Explanations

    variable `ans`

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

    The neuron fires on any token containing the letter sequence “ans” (e.g. identifiers or words with “ans” in them).

    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
     ใน
    -2.97
    ྅
    -2.80
    摃
    -2.44
     conquistar
    -2.42
     zahlreichen
    -2.39
    Utilisation
    -2.39
    焌
    -2.38
    けれ
    -2.38
     They
    -2.33
    是她
    -2.31
    POSITIVE LOGITS
    s
    3.88
    m
    3.67
    p
    3.59
    D
    3.34
    x
    3.31
    埽
    3.25
    j
    3.11
    E
    3.05
    O
    2.89
    re
    2.81
    Activations Density 0.011%

    No Known Activations