Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110380
    Prev
    Next
    INDEX
    Explanations

    UI components and code declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    btnBack
    -1.22
    btnLogin
    -1.19
    ButtonClicked
    -1.12
     Einen
    -0.97
    buttonText
    -0.96
    btnClose
    -0.96
    txtName
    -0.95
    pushButton
    -0.95
    textEdit
    -0.93
    ButtonClick
    -0.93
    POSITIVE LOGITS
     cancel
    1.06
     submit
    0.95
     unable
    0.88
     descrizione
    0.88
     kill
    0.88
    OK
    0.85
    IBOutlet
    0.85
    髅
    0.85
     delete
    0.84
    žia
    0.84
    Activations Density 0.006%

    No Known Activations