© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38816
    Prev
    Next
    INDEX
    Explanations

    developing or providing solutions

    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
     five
    -1.41
     three
    -1.41
    They
    -1.41
    With
    -1.39
     two
    -1.39
     both
    -1.38
     want
    -1.38
     this
    -1.36
     by
    -1.36
     that
    -1.36
    POSITIVE LOGITS
     mostrarán
    1.16
    っている
    1.13
     mientras
    1.09
    nitzel
    1.08
    atzes
    1.07
     hahaha
    1.05
     vocales
    1.04
    ᥱ
    1.02
    Keine
    1.01
    Kein
    1.00
    Activations Density 0.122%

    No Known Activations