© 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. 22-GEMMASCOPE-RES-131K
    7. 71861
    Prev
    Next
    INDEX
    Explanations

    describing requirements or actions

    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_22/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
    èses
    -0.98
    Quelques
    -0.94
     conspic
    -0.93
    çons
    -0.91
     karaoke
    -0.88
     그것
    -0.88
     gäng
    -0.88
    Trama
    -0.86
     hilar
    -0.85
    イエロー
    -0.85
    POSITIVE LOGITS
     this
    1.81
     even
    1.16
     continued
    1.14
     inserted
    1.13
     these
    1.12
     paragraph
    1.12
     including
    1.03
     many
    1.02
     here
    1.00
     their
    0.99
    Activations Density 0.098%

    No Known Activations