© 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. 67644
    Prev
    Next
    INDEX
    Explanations

    Give/update/correct information

    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
     Cedex
    -1.09
    Răspunde
    -1.07
     but
    -1.00
     or
    -1.00
    pust
    -0.96
    /
    -0.92
     MethodInfo
    -0.92
    時間の
    -0.91
    шки
    -0.91
    𝙞
    -0.90
    POSITIVE LOGITS
     everything
    1.79
     accordingly
    1.30
     everybody
    1.26
     what
    1.23
     whatever
    1.20
    そして
    1.16
     things
    1.16
     others
    1.14
     everywhere
    1.13
     everyone
    1.08
    Activations Density 0.026%

    No Known Activations