© 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. 12877
    Prev
    Next
    INDEX
    Explanations

    code and text snippets

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

    The neuron is primarily detecting line‐break tokens (e.g. carriage returns/newline characters).

    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
    0
    -4.50
    2
    -3.41
    1
    -3.41
    3
    -3.22
     After
    -3.00
     -
    -2.98
    After
    -2.92
    を
    -2.89
     Before
    -2.88
    7
    -2.86
    POSITIVE LOGITS
    s
    3.56
    歘
    3.25
    🫢
    3.08
     maniere
    2.95
     bezpeč
    2.92
     汽车
    2.91
    踯
    2.89
    ㅈ
    2.86
    蹰
    2.84
    癭
    2.84
    Activations Density 0.063%

    No Known Activations