© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63998
    Prev
    Next
    INDEX
    Explanations

    options, identifiers, or sequences

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

    The neuron fires on code identifiers that contain or start with uppercase letters (e.g. CamelCase or PascalCase variable, function, and type names).

    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
     Relatively
    -1.01
     new
    -0.93
     ponieważ
    -0.93
    Surprisingly
    -0.92
     комна
    -0.92
    啄
    -0.90
    Millan
    -0.90
     Και
    -0.90
     Apparently
    -0.90
     breiten
    -0.90
    POSITIVE LOGITS
    )
    1.25
    谢谢
    1.05
     Unito
    1.02
    ,</
    1.02
     saisons
    0.94
     paloma
    0.94
    }
    0.93
    ())
    0.92
    ')
    0.91
     _)
    0.90
    Activations Density 0.008%

    No Known Activations