© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118674
    Prev
    Next
    INDEX
    Explanations

    you asserting statements

    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
    我們
    -1.43
     ourselves
    -1.35
     или
    -1.30
    gegangen
    -1.13
     ‪
    -1.12
     нынеш
    -1.08
    inerario
    -1.08
    或
    -1.05
     کردند
    -1.03
    zembro
    -1.02
    POSITIVE LOGITS
    Assume
    1.20
     Assume
    1.20
     his
    1.17
     has
    1.16
     college
    1.14
     recently
    1.14
     your
    1.12
    XYZ
    1.12
     XYZ
    1.09
     Suppose
    1.07
    Activations Density 0.101%

    No Known Activations