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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 75379
    Prev
    Next
    INDEX
    Explanations

    it is / it was / it's

    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
     this
    -2.11
     it
    -1.60
    swire
    -1.58
     which
    -1.52
     diesmal
    -1.47
    🤨
    -1.27
    ícias
    -1.26
    ⁉
    -1.26
     groots
    -1.21
     sababu
    -1.21
    POSITIVE LOGITS
     a
    1.63
     also
    1.51
     alltså
    1.17
    来到了
    1.16
    などは
    1.16
     not
    1.16
     such
    1.15
    などが
    1.13
     پروفایل
    1.09
     basically
    1.08
    Activations Density 0.051%

    No Known Activations