© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 34163
    Prev
    Next
    INDEX
    Explanations

    childhood and youth

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

    The neuron fires strongly on words and phrases invoking childhood or childishness (e.g. kid, baby, child, childish).

    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
    v
    -1.11
    li
    -1.07
    人士
    -1.02
    ma
    -1.01
    ds
    -0.98
    lo
    -0.96
    se
    -0.96
    ss
    -0.95
    sa
    -0.94
    d
    -0.93
    POSITIVE LOGITS
     immature
    1.46
     childish
    1.39
     cukru
    1.25
     when
    1.23
     शुर
    1.16
    when
    1.16
     childhood
    1.14
    เด็ก
    1.13
     elementary
    1.12
     youthful
    1.11
    Activations Density 0.019%

    No Known Activations