© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65284
    Prev
    Next
    INDEX
    Explanations

    its, it, its, it

    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_22/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
     also
    -1.53
     then
    -1.45
     также
    -1.20
     которые
    -1.14
     which
    -1.14
     también
    -1.09
     também
    -1.09
     or
    -1.08
     також
    -1.02
     eventually
    -0.98
    POSITIVE LOGITS
     its
    2.00
    它
    1.69
    它的
    1.44
    Firstly
    1.42
    因为它
    1.25
     it
    1.18
    Its
    1.13
     เพราะ
    1.09
     потому
    1.07
    久し
    1.05
    Activations Density 0.061%

    No Known Activations