© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 12138
    Prev
    Next
    INDEX
    Explanations

    mojo plugin, springboot jpa, TPS recommendations, vocals, vaginal delivery

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

    The neuron fires strongly on software‐library, framework, or plugin names and other technical jargon identifiers.

    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
    
    -3.13
    怱
    -2.78
    '])
    -2.69
    ();
    -2.67
    ];
    -2.63
    -2.63
    埽
    -2.56
     is
    -2.56
    
    -2.52
    肏
    -2.50
    POSITIVE LOGITS
    F
    2.98
    H
    2.67
    на
    2.58
    B
    2.48
    These
    2.39
    🦥
    2.30
    ка
    2.30
    D
    2.25
     schlechte
    2.20
    驟
    2.19
    Activations Density 0.009%

    No Known Activations