© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 90642
    Prev
    Next
    INDEX
    Explanations

    pronouns and imperatives

    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_10/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
    </em>
    -1.57
    This
    -1.47
     for
    -1.43
    But
    -1.37
     on
    -1.37
     this
    -1.27
     eeuw
    -1.24
     Και
    -1.23
     After
    -1.23
     sekaligus
    -1.22
    POSITIVE LOGITS
    向了
    1.58
    ſſen
    1.32
    又一次
    1.26
    也想
    1.26
     alimentaria
    1.25
    新た
    1.23
    ambién
    1.22
    rcv
    1.21
     mismos
    1.20
     démarrage
    1.20
    Activations Density 0.049%

    No Known Activations