© 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. 89875
    Prev
    Next
    INDEX
    Explanations

    shows contrast or absence

    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
     it
    -1.16
    ındaki
    -1.09
    '';
    -1.07
    vão
    -1.05
    jando
    -1.03
     zacht
    -1.02
    aş
    -0.99
     asociada
    -0.98
     moléculas
    -0.97
    ACZ
    -0.96
    POSITIVE LOGITS
     a
    3.36
     an
    1.80
     similar
    1.52
     very
    1.34
     no
    1.27
     identical
    1.25
     only
    1.24
     pronounced
    1.18
     myös
    1.16
     temperatures
    1.14
    Activations Density 0.275%

    No Known Activations