© 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. 68835
    Prev
    Next
    INDEX
    Explanations

    if you/there/I/my

    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
     obliga
    -1.46
     vermutlich
    -1.46
    赈
    -1.45
     möglicherweise
    -1.40
     ilumina
    -1.40
     administrativa
    -1.39
     ziemlich
    -1.39
    修復
    -1.36
     solicita
    -1.34
     mixture
    -1.33
    POSITIVE LOGITS
     I
    1.45
     of
    1.38
     who
    1.28
     addi
    1.21
    </em>
    1.21
    вший
    1.20
     ambao
    1.17
    趼
    1.16
     sarcas
    1.16
     occa
    1.16
    Activations Density 0.011%

    No Known Activations