© 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. 34-GEMMASCOPE-RES-131K
    7. 92998
    Prev
    Next
    INDEX
    Explanations

    saving and remembering state

    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
    kezik
    -0.90
    τουργ
    -0.78
    ATORY
    -0.77
    CheckIn
    -0.73
     Hailey
    -0.73
    ቱ
    -0.71
    SLO
    -0.71
    værk
    -0.71
    hael
    -0.71
    Uninstall
    -0.71
    POSITIVE LOGITS
     saved
    2.86
     remembered
    2.70
     remembers
    2.52
     remember
    2.50
     save
    2.30
     remembering
    2.22
     last
    2.20
     Remember
    2.11
    remember
    2.11
    saved
    2.09
    Activations Density 0.082%

    No Known Activations