© 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. 58602
    Prev
    Next
    INDEX
    Explanations

    special character delimiters

    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
     it
    -1.66
     históricas
    -1.47
    After
    -1.47
    adır
    -1.38
     desnuda
    -1.30
    </h5>
    -1.29
    With
    -1.28
     sagrado
    -1.27
    各種
    -1.25
     domés
    -1.24
    POSITIVE LOGITS
     valentin
    1.41
     alip
    1.38
     alho
    1.37
     kanak
    1.32
     geene
    1.30
     barri
    1.27
     actionTypes
    1.27
     haki
    1.26
     sains
    1.25
     domini
    1.23
    Activations Density 0.190%

    No Known Activations