© 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. 22-GEMMASCOPE-RES-131K
    7. 40370
    Prev
    Next
    INDEX
    Explanations

    past tense actions

    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
    u
    -2.03
     was
    -1.72
     if
    -1.53
    当時は
    -1.42
     あっ
    -1.42
     ‘‘
    -1.41
    e
    -1.36
     letzt
    -1.32
     была
    -1.31
    騷
    -1.31
    POSITIVE LOGITS
     since
    2.09
     the
    2.08
    '
    1.66
     sejak
    1.60
     tagit
    1.59
     to
    1.55
     lately
    1.55
    傒
    1.50
     depuis
    1.50
     sinds
    1.46
    Activations Density 0.194%

    No Known Activations