© 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. 11757
    Prev
    Next
    INDEX
    Explanations

    Grav, Gab, Sav, Trav prefixes

    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
     Their
    -2.67
     ilumina
    -2.56
    趼
    -2.55
     incorporado
    -2.48
     celebrado
    -2.47
    felpa
    -2.42
    ༐
    -2.41
     lanzó
    -2.38
     firmado
    -2.34
     burbu
    -2.33
    POSITIVE LOGITS
    O
    3.05
    甞
    3.05
    栳
    2.73
    蹚
    2.63
    ꜆
    2.55
    艄
    2.53
    癭
    2.53
    蘗
    2.44
    aro
    2.44
    มากๆ
    2.36
    Activations Density 0.003%

    No Known Activations