© 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. 34-GEMMASCOPE-RES-131K
    7. 76084
    Prev
    Next
    INDEX
    Explanations

    be verb + being

    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
    算是
    -0.87
     県
    -0.85
     möglich
    -0.85
     máme
    -0.85
    croix
    -0.84
    secta
    -0.84
    ktioner
    -0.84
     laajenta
    -0.83
    ropoda
    -0.83
    frac
    -0.83
    POSITIVE LOGITS
     being
    8.25
    being
    5.25
    Being
    4.66
     Being
    4.16
     BEING
    3.81
     sendo
    3.78
     siendo
    3.58
     essere
    3.56
     étant
    3.36
    被
    3.34
    Activations Density 0.281%

    No Known Activations