© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 113462
    Prev
    Next
    INDEX
    Explanations

    opening quotes and special characters

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

    The neuron fires strongly on single-character literals of punctuation or operator symbols (e.g. “:”, “\\”, “+”, “-”)—i.e. when a document token is a quoted single-character escape/operator symbol.

    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
     of
    -3.16
    </h3>
    -2.70
    ⚌
    -2.69
    苤
    -2.67
    </em>
    -2.59
     beberapa
    -2.58
     cadeira
    -2.45
    觏
    -2.45
    퐸
    -2.42
    敺
    -2.41
    POSITIVE LOGITS
    there
    3.16
    From
    2.89
    when
    2.80
    With
    2.78
    !!!!!
    2.75
    This
    2.52
    !!!!
    2.52
    ⤵
    2.48
    with
    2.44
    !!”
    2.39
    Activations Density 0.005%

    No Known Activations