© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 40089
    Prev
    Next
    INDEX
    Explanations

    part of a whole

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

    The neuron strongly activates on the word “portion” (and its plural “portions”) in the text.

    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
     desbloquear
    -2.42
     gebruik
    -2.36
    ственная
    -2.31
     lunghi
    -2.30
     eccellente
    -2.25
     encender
    -2.23
     bezpeč
    -2.20
     sicura
    -2.20
     criticism
    -2.20
     numerosas
    -2.19
    POSITIVE LOGITS
    …
    2.81
    ated
    2.78
     для
    2.69
    n
    2.69
    '
    2.59
    —
    2.58
     noting
    2.55
     für
    2.52
    .’
    2.48
    辚
    2.48
    Activations Density 0.009%

    No Known Activations