© 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. 15054
    Prev
    Next
    INDEX
    Explanations

    occurrence until

    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
     now
    -1.77
     вже
    -1.39
     уже
    -1.21
     ormai
    -1.11
     already
    -1.08
     сейчас
    -1.05
     also
    -1.02
    今は
    -1.02
    已经
    -0.98
    Already
    -0.98
    POSITIVE LOGITS
     until
    3.73
    until
    2.55
     UNTIL
    2.45
     Until
    2.39
    Until
    2.33
    直到
    2.28
     initially
    2.16
     jusqu
    2.06
     till
    2.02
     untill
    1.96
    Activations Density 0.086%

    No Known Activations