© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 67803
    Prev
    Next
    INDEX
    Explanations

    welcome and hello

    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
     both
    -1.25
     various
    -1.23
     other
    -1.22
     such
    -1.16
     some
    -1.13
     furthermore
    -1.09
     moreover
    -1.09
     but
    -1.06
     therefore
    -1.04
     plus
    -1.03
    POSITIVE LOGITS
     I
    1.13
    nienia
    1.10
     here
    1.10
    👋
    1.05
    Here
    1.04
    睒
    1.03
    を選
    1.02
    ühungen
    1.02
    herbe
    1.02
    Avez
    1.00
    Activations Density 0.070%

    No Known Activations