© 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. 34-GEMMASCOPE-RES-131K
    7. 118469
    Prev
    Next
    INDEX
    Explanations

    dissociation, Disclaimer, Disjunctive

    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_34/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
     Erkennt
    -1.37
     perigo
    -1.30
     myriad
    -1.30
    燹
    -1.27
     überprü
    -1.27
     entwick
    -1.27
     erklä
    -1.27
    嵛
    -1.26
     Надо
    -1.25
     decisive
    -1.24
    POSITIVE LOGITS
     Dis
    1.72
    Dis
    1.63
     DIS
    1.45
     dis
    1.27
     Diss
    1.10
     otto
    1.09
    dis
    1.08
    ’
    1.07
     sene
    1.05
    penuhi
    1.05
    Activations Density 0.071%

    No Known Activations