© 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. 44505
    Prev
    Next
    INDEX
    Explanations

    add, delete, write, move, play

    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
     when
    -1.82
     Desenvolvimento
    -1.57
     there
    -1.55
    inverno
    -1.52
     singoli
    -1.51
     lavoratori
    -1.45
    说起
    -1.44
     through
    -1.39
     then
    -1.38
     kartą
    -1.38
    POSITIVE LOGITS
     I
    1.68
    1
    1.63
     meinem
    1.54
     mexicanos
    1.51
    了一個
    1.45
     andere
    1.44
     españoles
    1.43
    眶
    1.43
     anderes
    1.41
     cubanos
    1.41
    Activations Density 0.093%

    No Known Activations