© 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. 79607
    Prev
    Next
    INDEX
    Explanations

    Indian and British place names

    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
    شود
    -1.63
    ꦤ
    -1.54
    ":"",
    -1.44
    इटम
    -1.43
    εις
    -1.42
     one
    -1.41
    ꜆
    -1.41
     décadas
    -1.39
     derrot
    -1.37
    ᠌
    -1.37
    POSITIVE LOGITS
    0
    1.78
    7
    1.66
     gefunden
    1.63
    1
    1.49
     includ
    1.43
     koi
    1.38
     gebeten
    1.38
    6
    1.35
     foll
    1.35
     esquerdo
    1.35
    Activations Density 0.080%

    No Known Activations