© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109021
    Prev
    Next
    INDEX
    Explanations

    model

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

    The neuron fires on Angular template tokens—component/directive names and binding attributes (e.g. ngModel, ngbDropdown, formGroup)—marking Angular-specific markup.

    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
     Monat
    -0.74
     Sta
    -0.74
     Clan
    -0.73
    كمة
    -0.72
    ersch
    -0.72
     ח
    -0.70
     Mare
    -0.70
     član
    -0.69
     ש
    -0.68
     submarine
    -0.68
    POSITIVE LOGITS
     model
    1.73
    Model
    1.63
    model
    1.52
    MODEL
    1.43
     models
    1.41
     Model
    1.35
     Models
    1.32
     مدل
    1.28
    Models
    1.27
     FormControl
    1.23
    Activations Density 0.038%

    No Known Activations