© 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. 22-GEMMASCOPE-RES-131K
    4. 79754
    Prev
    Next
    INDEX
    Explanations

    great and synonyms followed by positive descriptors

    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_22/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
     ansiedad
    -1.39
    }.
    
    -1.31
     ........
    -1.30
     blauwe
    -1.23
    ământ
    -1.22
    omorphisms
    -1.21
    lawayo
    -1.21
    の部分
    -1.21
     ilustraciones
    -1.20
     dalamnya
    -1.20
    POSITIVE LOGITS
    !
    2.27
    !!
    1.34
     very
    1.27
    !!!
    1.22
    2
    1.16
    4
    1.13
    次回
    1.12
    子は
    1.10
    5
    1.07
     initiatives
    1.05
    Activations Density 0.007%

    No Known Activations