© 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. 34-GEMMASCOPE-RES-131K
    7. 58412
    Prev
    Next
    INDEX
    Explanations

    can / could + verb

    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
     poder
    -1.13
     know
    -1.11
     can
    -1.09
     pouvoir
    -1.02
     having
    -1.02
    可以让
    -0.96
     could
    -0.95
    tså
    -0.89
     using
    -0.88
    墾
    -0.88
    POSITIVE LOGITS
     be
    2.06
     handle
    1.41
     been
    1.29
     accommodate
    1.25
     withstand
    1.23
     worden
    1.19
     используются
    1.16
    被
    1.12
     նաև
    1.12
     accomod
    1.08
    Activations Density 0.111%

    No Known Activations