© 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. 10-GEMMASCOPE-RES-131K
    7. 12133
    Prev
    Next
    INDEX
    Explanations

    erratic, inconsistent, or unreliable

    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
     disgruntled
    -1.63
    actéristi
    -1.58
     ответил
    -1.56
     pouvaient
    -1.52
    nější
    -1.52
     obligé
    -1.49
     Somebody
    -1.48
    
    -1.48
    
    -1.47
     engagé
    -1.44
    POSITIVE LOGITS
     reputación
    1.63
     on
    1.50
    and
    1.47
    )$
    1.42
     unreliable
    1.38
     korzyst
    1.33
     laikā
    1.28
     chica
    1.25
     encuent
    1.25
     encuentre
    1.24
    Activations Density 0.069%

    No Known Activations