© 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. 39459
    Prev
    Next
    INDEX
    Explanations

    created by / on

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

    The neuron activates strongly on long runs of whitespace (indentation) tokens in source code.

    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
     Políticas
    -1.40
    tabria
    -1.34
     ją
    -1.26
    ſſen
    -1.26
    CHREIB
    -1.18
    ACZ
    -1.18
     nieuwe
    -1.16
     romantis
    -1.16
     oferece
    -1.16
     энергии
    -1.16
    POSITIVE LOGITS
    '
    1.49
    P
    1.31
    ´
    1.30
    G
    1.23
    N
    1.23
    //
    1.22
    A
    1.20
    Y
    1.19
    M
    1.19
    1.19
    Activations Density 0.004%

    No Known Activations