© 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. 34-GEMMASCOPE-RES-131K
    7. 108341
    Prev
    Next
    INDEX
    Explanations

    citations and 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_34/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
     or
    -2.05
     this
    -1.95
     their
    -1.91
     that
    -1.89
     both
    -1.75
    なのかな
    -1.75
     there
    -1.72
     at
    -1.70
     all
    -1.69
     in
    -1.67
    POSITIVE LOGITS
    などが
    1.56
    Programma
    1.53
    がありますが
    1.49
    などを
    1.49
     resolução
    1.45
    Interes
    1.45
     occuper
    1.44
    但这
    1.42
    因为他
    1.40
     uniquement
    1.39
    Activations Density 0.032%

    No Known Activations