© 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. 22-GEMMASCOPE-RES-131K
    7. 14071
    Prev
    Next
    INDEX
    Explanations

    modelforms with attributes like model, form, validate

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

    This neuron fires strongly on Angular reactive‐form API tokens (like FormControl, FormGroup, fb.group, validator), i.e. code defining or using reactive form constructs.

    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
     was
    -1.72
    ?
    -1.42
    on
    -1.37
     marseille
    -1.36
    _
    -1.30
     cordoba
    -1.28
    ;
    -1.25
    //!
    -1.23
     frankfurt
    -1.21
    \
    -1.20
    POSITIVE LOGITS
     ascertaining
    1.31
    Determining
    1.27
    selben
    1.24
    Ông
    1.22
     depicting
    1.22
    顧客
    1.21
    viembre
    1.20
     menghubungi
    1.18
     Олег
    1.18
    *}[
    1.18
    Activations Density 0.002%

    No Known Activations