© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33104
    Prev
    Next
    INDEX
    Explanations

    sequence and outcome

    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
    urangi
    -0.90
     ГО
    -0.87
    Читать
    -0.84
    gamot
    -0.84
     РО
    -0.84
     honte
    -0.83
    zyka
    -0.82
     pioneered
    -0.82
    Often
    -0.81
     auparavant
    -0.81
    POSITIVE LOGITS
     then
    2.17
     later
    2.14
     subsequent
    1.90
     final
    1.86
     eventually
    1.77
     finally
    1.66
     subsequently
    1.64
     afterwards
    1.62
     thereafter
    1.57
     afterward
    1.45
    Activations Density 0.079%

    No Known Activations