© 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. 12487
    Prev
    Next
    INDEX
    Explanations

    verbs of mental state and observation

    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
     yatak
    -1.49
    :……
    -1.40
     tristesse
    -1.31
    pectiva
    -1.29
     my
    -1.29
     obvious
    -1.18
    ariously
    -1.18
    ↵↵↵↵
    -1.16
     chance
    -1.16
     nuanced
    -1.16
    POSITIVE LOGITS
     of
    1.89
     künftig
    1.30
     данного
    1.26
     március
    1.26
     Europy
    1.19
     zatem
    1.16
     princípios
    1.14
     cukru
    1.12
     henceforth
    1.11
    FFECT
    1.10
    Activations Density 0.102%

    No Known Activations