© 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. 65185
    Prev
    Next
    INDEX
    Explanations

    continued or began

    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
    今は
    -1.43
     currently
    -1.38
     demokra
    -1.36
     yesterday
    -1.35
     it
    -1.34
     you
    -1.30
     сейчас
    -1.25
    現在は
    -1.23
     aujourd
    -1.22
    Currently
    -1.22
    POSITIVE LOGITS
     continued
    2.48
     soon
    2.03
     continues
    1.90
     began
    1.70
     eventually
    1.66
     thereafter
    1.65
     gradually
    1.65
     continue
    1.63
     continuó
    1.56
     became
    1.51
    Activations Density 0.026%

    No Known Activations