© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 116589
    Prev
    Next
    INDEX
    Explanations

    programming types and keywords

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

    The neuron consistently flags Swift declarations’ type-annotation markers—i.e. the colons and related tokens used in class/var/func signatures and inheritance clauses.

    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
     accepte
    -0.97
     TÉ
    -0.93
     deuil
    -0.88
     INDEPENDENT
    -0.87
     @"
    -0.85
     kala
    -0.85
    ﹠
    -0.85
    Dx
    -0.85
    ligere
    -0.85
    ierungen
    -0.84
    POSITIVE LOGITS
     any
    1.60
     Any
    1.48
    Any
    1.42
     Int
    1.16
     in
    1.12
     String
    1.11
     [
    1.06
     ((
    1.05
     (
    0.97
     Bool
    0.96
    Activations Density 0.022%

    No Known Activations