© 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. 22-GEMMASCOPE-RES-131K
    7. 35118
    Prev
    Next
    INDEX
    Explanations

    input image

    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
    dibujos
    -1.27
    Saying
    -1.18
    来週
    -1.16
     captivated
    -1.10
     remarkably
    -1.09
     extremely
    -1.06
     incredibly
    -1.05
    谖
    -1.04
    俺は
    -1.03
     Verbraucher
    -1.03
    POSITIVE LOGITS
     with
    1.28
     galeria
    1.18
     bec
    1.06
    råd
    1.06
     at
    1.05
    硯
    1.04
    🎃
    1.04
    偲
    1.03
     alongside
    1.02
     Desember
    1.02
    Activations Density 0.110%

    No Known Activations