© 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. 69060
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and variables

    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
     by
    -1.48
     what
    -1.33
     using
    -1.28
     making
    -1.21
     or
    -1.20
     Going
    -1.20
     Even
    -1.20
     keeping
    -1.19
     after
    -1.18
     bringing
    -1.18
    POSITIVE LOGITS
     startling
    1.38
     vastly
    1.37
     sooo
    1.33
     DURING
    1.31
     legendar
    1.30
     strikingly
    1.30
     insanely
    1.30
     lauded
    1.29
     verschillende
    1.28
     alcune
    1.28
    Activations Density 0.007%

    No Known Activations