© 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. 65817
    Prev
    Next
    INDEX
    Explanations

    past tense verbs indicating action or state

    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
     duży
    -1.37
     więks
    -1.34
     cualquier
    -1.31
     nachdem
    -1.30
     someone
    -1.27
     ранее
    -1.26
     después
    -1.22
     infolge
    -1.20
     często
    -1.18
     meistens
    -1.18
    POSITIVE LOGITS
     from
    1.52
    taient
    1.35
     himself
    1.33
    ‧
    1.30
     vuitton
    1.26
    >?
    1.23
    вані
    1.23
    ்
    1.22
    ynchronously
    1.20
    に
    1.20
    Activations Density 0.047%

    No Known Activations