© 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. 71035
    Prev
    Next
    INDEX
    Explanations

    invention Designers

    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
     that
    -1.10
     présent
    -0.98
    Geographie
    -0.95
     menikmati
    -0.94
    הע
    -0.93
    avantage
    -0.92
    dinga
    -0.92
     regeringen
    -0.90
     Similarly
    -0.90
    conditions
    -0.89
    POSITIVE LOGITS
    鴦
    0.94
    kpop
    0.91
     côtes
    0.90
    ’
    0.90
    рим
    0.90
     salat
    0.88
    yā
    0.88
    })-
    0.87
     shui
    0.85
     فهرست
    0.85
    Activations Density 0.000%

    No Known Activations