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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74479
    Prev
    Next
    INDEX
    Explanations

    month 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_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
    .---
    -2.47
    tedì
    -2.34
     Ähn
    -2.20
     multitude
    -2.19
     WITH
    -2.19
     was
    -2.19
     beinahe
    -2.13
    一旁
    -2.09
    anthin
    -2.09
     isn
    -2.08
    POSITIVE LOGITS
    釓
    2.70
    at
    2.56
    齮
    2.50
    olge
    2.48
    
    2.44
     liet
    2.42
    镡
    2.39
     laat
    2.39
     correspondant
    2.38
    ayaquil
    2.28
    Activations Density 0.029%

    No Known Activations