© 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. 34-GEMMASCOPE-RES-131K
    7. 116652
    Prev
    Next
    INDEX
    Explanations

    among the many

    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_34/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
     as
    -1.17
     each
    -1.07
    ১
    -1.05
     both
    -1.05
    两个
    -1.05
     or
    -1.02
     can
    -1.00
    每个
    -0.99
     just
    -0.98
     seseorang
    -0.98
    POSITIVE LOGITS
    MANY
    1.51
     nombreuses
    1.37
     variety
    1.29
     wielu
    1.26
     여러
    1.25
     ranks
    1.23
     MANY
    1.23
     many
    1.23
     few
    1.22
     myriad
    1.21
    Activations Density 0.044%

    No Known Activations