© 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. 95542
    Prev
    Next
    INDEX
    Explanations

    numbers following other numbers or tokens

    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
    嗚
    -1.32
    zdo
    -1.26
    넋
    -1.20
     or
    -1.20
     trimestre
    -1.19
     biela
    -1.17
     in
    -1.13
     their
    -1.13
     tiap
    -1.12
     vesel
    -1.12
    POSITIVE LOGITS
    1
    1.33
    w
    1.30
    g
    1.30
    7
    1.28
    0
    1.27
    8
    1.27
    5
    1.19
     vorigen
    1.15
    ay
    1.15
    is
    1.15
    Activations Density 0.000%

    No Known Activations