© 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. 22-GEMMASCOPE-RES-131K
    7. 104239
    Prev
    Next
    INDEX
    Explanations

    asking about topics

    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
     at
    -1.18
    essentiel
    -1.14
     by
    -1.09
     in
    -1.08
     through
    -1.05
     volledige
    -0.96
    gilet
    -0.96
     reconnaît
    -0.96
    ↵
    -0.96
     viață
    -0.95
    POSITIVE LOGITS
     your
    1.09
     discussion
    1.06
     Psicología
    1.05
     this
    0.99
     discussions
    0.96
    caid
    0.95
     eventualmente
    0.90
     kommende
    0.89
    uso
    0.88
     inmediatamente
    0.88
    Activations Density 0.079%

    No Known Activations