© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67475
    Prev
    Next
    INDEX
    Explanations

    communication verbs and nouns

    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
    2
    -2.30
    also
    -2.03
    V
    -1.98
    3
    -1.94
     likewise
    -1.91
    必要な
    -1.89
     brauche
    -1.88
     saker
    -1.84
     was
    -1.83
     других
    -1.83
    POSITIVE LOGITS
    ܃
    2.30
    龗
    2.28
     $^{\
    2.23
    というわけで
    2.13
     parachoque
    2.09
    龱
    2.06
     夜景
    2.05
    ݯ
    2.03
    
    2.02
    茘
    2.02
    Activations Density 0.016%

    No Known Activations