© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110650
    Prev
    Next
    INDEX
    Explanations

    code comments and 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
    ῾
    -0.88
     jonka
    -0.88
    ieważ
    -0.81
    ̾
    -0.81
    XCTAssertEqual
    -0.81
     innego
    -0.81
    bindingNavigator
    -0.81
    >"
    -0.80
     станции
    -0.77
     naszego
    -0.77
    POSITIVE LOGITS
    private
    1.17
     a
    0.80
    ///
    0.77
    //
    0.76
     Capa
    0.75
    kna
    0.75
    涩
    0.73
     amends
    0.72
     misuse
    0.71
     Anam
    0.71
    Activations Density 0.001%

    No Known Activations