© 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. 10-GEMMASCOPE-RES-131K
    7. 1614
    Prev
    Next
    INDEX
    Explanations

    application, incident, converted

    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
    Also
    -1.62
     sogar
    -1.59
     also
    -1.59
    Even
    -1.58
    even
    -1.53
     даже
    -1.51
     также
    -1.45
    Other
    -1.43
    Its
    -1.43
    see
    -1.42
    POSITIVE LOGITS
     who
    1.63
     bolsillos
    1.48
     ἄ
    1.46
    犼
    1.42
     whom
    1.40
    ïc
    1.40
    𓁹
    1.38
     billetes
    1.36
    \'{
    1.36
    同様
    1.32
    Activations Density 0.120%

    No Known Activations