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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99614
    Prev
    Next
    INDEX
    Explanations

    identifies "this is" constructions

    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
     such
    -1.18
     even
    -1.07
     does
    -1.03
     any
    -0.97
     When
    -0.96
     things
    -0.95
     makes
    -0.95
     one
    -0.92
     more
    -0.92
     veci
    -0.92
    POSITIVE LOGITS
     это
    3.25
    这是
    2.97
    這是
    2.78
     đây
    2.61
    これは
    2.34
     it
    2.22
     Это
    2.16
     this
    2.14
    这是一
    2.11
    Это
    2.09
    Activations Density 0.110%

    No Known Activations