© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72495
    Prev
    Next
    INDEX
    Explanations

    n followed by a space or word

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

    The neuron is keyed to the literal “n” token—i.e. it picks up newline/line‐break markers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     is
    -2.89
     when
    -2.28
    x
    -2.19
     this
    -2.11
     як
    -2.08
     or
    -2.06
     और
    -2.05
     during
    -2.02
     we
    -1.99
     because
    -1.94
    POSITIVE LOGITS
    ኧ
    2.09
    𐬹
    2.03
    饧
    1.91
    蚰
    1.89
    呶
    1.87
     léger
    1.78
    ☫
    1.69
    佺
    1.69
    能在
    1.68
    媼
    1.68
    Activations Density 0.028%

    No Known Activations