© 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. 93218
    Prev
    Next
    INDEX
    Explanations

    persistent storage

    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
     ginge
    -1.04
     FEEDBACK
    -0.97
     נוספת
    -0.96
     jene
    -0.94
    蟥
    -0.93
     principali
    -0.89
     maniere
    -0.88
     supposed
    -0.88
    搔
    -0.88
     assumed
    -0.88
    POSITIVE LOGITS
     persist
    1.68
    persist
    1.47
     persistence
    1.40
     Persistence
    1.31
     persistent
    1.30
     persever
    1.29
    persistent
    1.28
    Persistent
    1.25
     persisted
    1.24
     Persistent
    1.23
    Activations Density 0.018%

    No Known Activations