© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72810
    Prev
    Next
    INDEX
    Explanations

    insurance company or policy

    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
    】:
    -1.86
     causando
    -1.56
     gustos
    -1.51
     &
    -1.49
    虽
    -1.47
    灯光
    -1.46
     provocando
    -1.45
    及び
    -1.41
     welt
    -1.37
     unwarranted
    -1.36
    POSITIVE LOGITS
    this
    1.94
     antworte
    1.89
     nostro
    1.84
    that
    1.80
     ersche
    1.66
     αυτή
    1.66
     menschliche
    1.63
    those
    1.60
    ción
    1.60
    </h3>
    1.60
    Activations Density 0.181%

    No Known Activations