© 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. 75006
    Prev
    Next
    INDEX
    Explanations

    code and numbers separators

    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
    -1.09
     by
    -1.02
     in
    -1.01
     from
    -0.98
     with
    -0.98
     and
    -0.96
     because
    -0.91
     preferências
    -0.91
     Because
    -0.88
    Concluding
    -0.87
    POSITIVE LOGITS
     tumultuous
    1.14
     plusieurs
    1.11
     inizio
    1.08
    アルミ
    1.06
    Références
    1.05
     seiz
    1.04
     harrowing
    1.03
     elektrik
    1.02
     desempeño
    1.02
     sfondo
    1.02
    Activations Density 0.116%

    No Known Activations