© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91384
    Prev
    Next
    INDEX
    Explanations

    greater... the more

    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
     a
    -1.55
     its
    -1.16
     главным
    -1.13
     it
    -1.05
     an
    -1.02
     their
    -0.96
     this
    -0.92
     your
    -0.90
    
    -0.90
     Herausgeber
    -0.90
    POSITIVE LOGITS
     the
    4.66
    the
    1.48
     чем
    1.41
    The
    1.25
    Чем
    1.23
    rethe
    1.13
     maladie
    1.11
    (≧
    1.10
    ethe
    1.10
    enthe
    1.09
    Activations Density 0.060%

    No Known Activations