© 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. 22-GEMMASCOPE-RES-131K
    7. 14431
    Prev
    Next
    INDEX
    Explanations

    second consecutive

    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
     usually
    -1.51
     various
    -1.31
     vielleicht
    -1.25
     Usually
    -1.24
    Usually
    -1.19
     обычно
    -1.16
     which
    -1.15
     any
    -1.09
     typically
    -1.09
     either
    -1.07
    POSITIVE LOGITS
    милия
    1.06
     identical
    1.05
     consecutive
    1.03
    agliari
    0.98
     in
    0.97
    同样的
    0.93
     подряд
    0.92
    このような
    0.91
    룬
    0.88
     같은
    0.87
    Activations Density 0.040%

    No Known Activations