© 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. 314
    Prev
    Next
    INDEX
    Explanations

    ; DO NOT EDIT

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

    The neuron primarily detects semicolon punctuation marks (i.e. “;”) as statement terminators.

    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
    <bos>
    -1.17
     évé
    -1.11
     bandes
    -1.09
    ــــــــ
    -1.05
    źdz
    -1.05
    他們
    -1.03
    ↓
    -1.02
    ایک
    -1.00
     Rússia
    -0.99
     الذي
    -0.99
    POSITIVE LOGITS
     ;
    1.59
    );
    1.41
    $;
    1.28
    ;;;;
    1.19
    _;
    1.19
    --
    1.17
    ;;
    1.16
    "]
    1.16
    ).
    1.12
    ))
    1.10
    Activations Density 0.087%

    No Known Activations