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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 710
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     morreu
    -1.01
     brilhante
    -0.95
    consin
    -0.95
     müßte
    -0.94
     recém
    -0.93
    chra
    -0.92
     серь
    -0.90
    Mask
    -0.90
     agradável
    -0.88
     passou
    -0.88
    POSITIVE LOGITS
     recomend
    0.98
     VIDEOT
    0.94
    会
    0.92
     grise
    0.92
     scru
    0.91
    jaard
    0.91
    zeigt
    0.91
     Zeich
    0.89
     rabb
    0.89
    默认
    0.89
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.