© 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. 22-GEMMASCOPE-RES-131K
    7. 28170
    Prev
    Next
    INDEX
    Explanations

    whether independent

    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
    necedor
    -0.98
    了她
    -0.90
    angerie
    -0.90
    ariats
    -0.87
    
    -0.86
     insinu
    -0.85
    ">—
    -0.85
    вим
    -0.84
     correspon
    -0.82
    uating
    -0.82
    POSITIVE LOGITS
     any
    1.26
     except
    1.11
     apapun
    1.03
     quaisquer
    1.02
    Any
    1.02
     location
    1.02
     whether
    1.02
    也不會
    0.99
     qualquer
    0.98
     unless
    0.97
    Activations Density 0.047%

    No Known Activations