© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 35514
    Prev
    Next
    INDEX
    Explanations

    code punctuation and types

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

    The neuron is selectively activating on numeric literals (and adjacent punctuation/operators) in code snippets.

    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
     Новосибир
    -1.22
     andata
    -1.09
    ,
    -1.05
     قوات
    -1.03
     lee
    -0.99
     andato
    -0.92
     and
    -0.91
    WebElementEntity
    -0.90
     on
    -0.89
     programu
    -0.88
    POSITIVE LOGITS
    タグ
    1.14
    ))));
    1.10
    。
    1.05
    })));
    1.05
    ։
    1.03
    >');
    1.03
    ;
    
    1.03
    orsese
    1.02
     emosi
    1.00
     dinas
    1.00
    Activations Density 0.010%

    No Known Activations