© 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. 129195
    Prev
    Next
    INDEX
    Explanations

    modal verbs followed by get or be

    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
     itself
    -1.57
     atriz
    -1.47
     you
    -1.30
     cantora
    -1.20
     erzä
    -1.20
     our
    -1.16
    様でした
    -1.16
     tirage
    -1.15
     bisous
    -1.13
     Dacă
    -1.10
    POSITIVE LOGITS
     have
    2.09
     được
    1.76
     able
    1.74
     can
    1.69
     need
    1.63
     thấy
    1.52
    能够
    1.51
    ได้
    1.49
     pouvoir
    1.44
     get
    1.40
    Activations Density 0.076%

    No Known Activations