© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 23465
    Prev
    Next
    INDEX
    Explanations

    command prompt %%G

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

    This neuron detects Lisp-style format escape sequences (the “~” directives) in 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_34/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
    "]["
    -0.76
    褻
    -0.74
     ít
    -0.68
    ='".$
    -0.68
    oglu
    -0.65
     amarilla
    -0.64
    ílica
    -0.64
     wikipagina
    -0.64
     morgen
    -0.63
    koon
    -0.63
    POSITIVE LOGITS
    ~
    3.09
     ~
    3.02
    ~,
    2.48
    )~
    2.31
    ~$
    2.31
    ~.
    2.28
    .~
    2.25
     "~
    2.17
     ~(
    2.13
    ~)
    2.11
    Activations Density 0.048%

    No Known Activations