© 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. 22-GEMMASCOPE-RES-131K
    7. 129344
    Prev
    Next
    INDEX
    Explanations

    phrases starting with certain tokens

    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
    atangan
    -1.03
    wakili
    -0.98
    dengan
    -0.97
    opportunities
    -0.96
     paru
    -0.95
     sobot
    -0.95
    🎣
    -0.94
     PÉ
    -0.92
     typy
    -0.91
     minas
    -0.91
    POSITIVE LOGITS
     humans
    0.96
    
    0.94
     needed
    0.92
     gegenüber
    0.90
    anskrit
    0.89
     człowiek
    0.88
    MLElement
    0.85
    8
    0.85
    ciata
    0.84
     Treatise
    0.83
    Activations Density 0.000%

    No Known Activations