© 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. 68092
    Prev
    Next
    INDEX
    Explanations

    starting words and phrases in text

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

    The neuron responds strongly to the special whitespace (indentation) character.

    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
    ओं
    -1.13
    deuse
    -1.05
     sodio
    -1.03
     verso
    -1.02
    нули
    -1.00
     perpé
    -1.00
     elever
    -1.00
     töö
    -0.97
     Achter
    -0.97
     Cups
    -0.96
    POSITIVE LOGITS
    뭘
    1.16
     and
    1.16
     or
    1.16
     protože
    1.05
     variedades
    0.96
     generaciones
    0.96
    deutig
    0.96
    灃
    0.96
     posled
    0.94
     at
    0.94
    Activations Density 0.000%

    No Known Activations