© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103984
    Prev
    Next
    INDEX
    Explanations

    reminding us or yourself

    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_10/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
    "
    -1.97
     t
    -1.97
    ).
    -1.91
    2
    -1.90
    ка
    -1.84
    %
    -1.77
     strangest
    -1.75
    ]
    -1.72
    }$.
    -1.70
     уже
    -1.68
    POSITIVE LOGITS
    gulation
    2.27
    vocations
    2.23
    鲥
    2.16
    sandalia
    2.14
     polie
    2.05
    桖
    2.05
     baumwolle
    2.03
    hibited
    1.99
    vention
    1.99
     gode
    1.95
    Activations Density 0.007%

    No Known Activations