© 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. 71391
    Prev
    Next
    INDEX
    Explanations

    positions and leaders

    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
     each
    -1.05
     CURIAM
    -0.98
    每个
    -0.94
    Each
    -0.93
     offiziellen
    -0.88
     individuellen
    -0.87
     zarówno
    -0.86
     pione
    -0.85
    дость
    -0.85
     ragazza
    -0.84
    POSITIVE LOGITS
     who
    1.20
     yerine
    1.01
     nieuw
    0.94
    )':
    0.94
     qualified
    0.93
     вместо
    0.91
     blandt
    0.91
     ciudadanos
    0.90
     from
    0.90
    符合
    0.89
    Activations Density 0.069%

    No Known Activations