© 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. 65807
    Prev
    Next
    INDEX
    Explanations

    modal verbs and possibility

    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
     when
    -1.30
     persen
    -1.12
     are
    -1.09
    dienne
    -1.08
    Typically
    -1.03
     længere
    -1.03
    Demografie
    -1.02
    ⢁
    -1.02
     magasiner
    -0.98
    дают
    -0.98
    POSITIVE LOGITS
     would
    2.47
     then
    2.02
     wäre
    1.63
     lenne
    1.52
     тогда
    1.52
     could
    1.49
     instead
    1.48
     endlich
    1.39
     help
    1.34
     sería
    1.32
    Activations Density 0.021%

    No Known Activations