© 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. 3281
    Prev
    Next
    INDEX
    Explanations

    code creation

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

    The neuron flags programming identifiers (e.g. class‐, type‐, or method‐name tokens) 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
    Poe
    -0.84
     беше
    -0.82
    周泽楷
    -0.81
    ـــ
    -0.80
     grabs
    -0.78
    SerialNumber
    -0.77
    散歩
    -0.77
     atra
    -0.77
     לט
    -0.76
    퀸
    -0.75
    POSITIVE LOGITS
    Bounding
    0.75
     diduga
    0.73
    篇
    0.71
     hampir
    0.71
    nz
    0.69
    👂
    0.68
     technische
    0.68
    McL
    0.68
     военно
    0.68
    Aspect
    0.67
    Activations Density 0.120%

    No Known Activations