© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22634
    Prev
    Next
    INDEX
    Explanations

    Premier followed by a specific noun

    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
    Negative Logits
    "
    -2.63
    ꜆
    -2.56
     kteří
    -2.53
     forlorn
    -2.48
    said
    -2.44
     dangers
    -2.41
     bezpeč
    -2.39
    ꔹ
    -2.34
     doskona
    -2.33
    ῞
    -2.33
    POSITIVE LOGITS
    鶲
    3.22
    ”،
    2.95
    ing
    2.95
    洐
    2.80
    ୈ
    2.77
    芣
    2.67
    ቭ
    2.67
    沇
    2.63
    ة
    2.58
    媜
    2.58
    Activations Density 0.004%

    No Known Activations