© 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. 118663
    Prev
    Next
    INDEX
    Explanations

    == and comparisons

    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
     isn
    -2.09
     !=
    -1.94
     aren
    -1.82
     не
    -1.82
     not
    -1.78
     wasn
    -1.77
     !==
    -1.74
     não
    -1.73
    不是
    -1.72
     weren
    -1.69
    POSITIVE LOGITS
     ==
    1.94
    assertNull
    1.59
    ==
    1.41
     ===
    1.38
     is
    1.34
    ()==
    1.27
    ]==
    1.25
    ")==
    1.19
     was
    1.17
    isEmpty
    1.17
    Activations Density 0.015%

    No Known Activations